A Concise and Varied Visual Features-Based Image Captioning Model with Visual Selection

Image captioning has gained increasing attention in recent years.Visual characteristics found in input images play a crucial role in generating high-quality captions.Prior studies have used visual attention mechanisms to dynamically focus on localized regions of the input image,improving the effectiveness of identifying relevant image regions at each step of caption generation.However,providing image captioning models with the capability of selecting the most relevant visual features from the input image and attending to them can significantly improve the utilization of these features.Consequently,this leads to enhanced captioning network performance.In light of this,we present an image captioning framework that efficiently exploits the extracted representations of the image.Our framework comprises three key components:the Visual Feature Detector module(VFD),the Visual Feature Visual Attention module(VFVA),and the language model.The VFD module is responsible for detecting a subset of the most pertinent features from the local visual features,creating an updated visual features matrix.Subsequently,the VFVA directs its attention to the visual features matrix generated by the VFD,resulting in an updated context vector employed by the language model to generate an informative description.Integrating the VFD and VFVA modules introduces an additional layer of processing for the visual features,thereby contributing to enhancing the image captioning model’s performance.Using the MS-COCO dataset,our experiments show that the proposed framework competes well with state-of-the-art methods,effectively leveraging visual representations to improve performance.The implementation code can be found here:https://github.com/althobhani/VFDICM(accessed on 30 July 2024).

Enhancing visual security: An image encryption scheme based on parallel compressive sensing and edge detection embedding

A novel image encryption scheme based on parallel compressive sensing and edge detection embedding technology is proposed to improve visual security. Firstly, the plain image is sparsely represented using the discrete wavelet transform.Then, the coefficient matrix is scrambled and compressed to obtain a size-reduced image using the Fisher–Yates shuffle and parallel compressive sensing. Subsequently, to increase the security of the proposed algorithm, the compressed image is re-encrypted through permutation and diffusion to obtain a noise-like secret image. Finally, an adaptive embedding method based on edge detection for different carrier images is proposed to generate a visually meaningful cipher image. To improve the plaintext sensitivity of the algorithm, the counter mode is combined with the hash function to generate keys for chaotic systems. Additionally, an effective permutation method is designed to scramble the pixels of the compressed image in the re-encryption stage. The simulation results and analyses demonstrate that the proposed algorithm performs well in terms of visual security and decryption quality.

Importance-aware 3D volume visualization for medical content-based image retrieval-a preliminary study

Background A medical content-based image retrieval(CBIR)system is designed to retrieve images from large imaging repositories that are visually similar to a user′s query image.CBIR is widely used in evidence-based diagnosis,teaching,and research.Although the retrieval accuracy has largely improved,there has been limited development toward visualizing important image features that indicate the similarity of retrieved images.Despite the prevalence of 3D volumetric data in medical imaging such as computed tomography(CT),current CBIR systems still rely on 2D cross-sectional views for the visualization of retrieved images.Such 2D visualization requires users to browse through the image stacks to confirm the similarity of the retrieved images and often involves mental reconstruction of 3D information,including the size,shape,and spatial relations of multiple structures.This process is time-consuming and reliant on users'experience.Methods In this study,we proposed an importance-aware 3D volume visualization method.The rendering parameters were automatically optimized to maximize the visibility of important structures that were detected and prioritized in the retrieval process.We then integrated the proposed visualization into a CBIR system,thereby complementing the 2D cross-sectional views for relevance feedback and further analyses.Results Our preliminary results demonstrate that 3D visualization can provide additional information using multimodal positron emission tomography and computed tomography(PETCT)images of a non-small cell lung cancer dataset.

A Study on the Influence of Patterned Logo Design on Brand Image-Focused on the Li Ning Brand

In today’s flood of information,people mainly rely on visual information to recognize brands.Pattern logo design is a representative brand image and directly affects consumers’brand impression and perception.The purpose of this study is to examine the characteristics of the Li Ning brand and the effect of pattern logo design on the brand image.Specifically,it is to provide practical guidelines for brand management and design by analyzing the effects on brand perception,emotional connection,and consumer behavior.For the scope of the study,seven brands are selected for analysis of famous brand cases at home and abroad.The research method is to design a patterned logo suitable for brand characteristics through literature review,empirical research,and detailed analysis of the overall style characteristics of the current Li Ning brand.The research content first analyzes the role of pattern logo design in terms of brand perception,brand perception,and brand sensitivity.Subsequently,the evolution and effect of the Li Ning brand in logo design are examined,and details are discussed in combination with the color and shape of the logo pattern.Finally,by presenting some suggestions and optimized design plans that fit the characteristics and trends of the Li Ning brand,the brand image and market competitiveness can be improved.According to the research results,first,the color,shape,and other factors of brand pattern logo design are closely related to brand image.Second,pattern logo design has a significant influence on consumer attitudes and purchase intentions.Third,consumers are more interested in the design of a patterned logo with high brand awareness.This study has a certain significance in that it reveals the mechanism by which pattern logo design affects brand image and provides useful ideas and suggestions for brand design and marketing.

Emotionally Resonant Branding: The Role of AI in Synthesising Dynamic Brand Images for Artists in the Music Industry

Artificial Intelligence (AI) expands its recognition rapidly through the past few years in the context of generating content dynamically, remarkably challenging the human creativity. This study aims to evaluate the efficacy of AI in enhancing personal branding for musicians, particularly in crafting brand images based on emotions received from the artist’s music will improve the audience perceptions regarding the artist’s brand. Study used a quantitative approach for the research, gathering primary data from the survey of 191 people—music lovers, musicians and music producers. The survey focuses on preferences, perceptions, and behaviours related to music consumption and artist branding. The study results demonstrate the awareness and understanding of AI’s role in personal branding within the music industry. Also, results indicate that such an adaptive approach enhances audience perceptions of the artist and strengthens emotional connections. Furthermore, over 50% of the participants indicated a desire to attend live events where an artist’s brand image adapts dynamically to their emotions. The study focuses on novel approaches in personal branding based on the interaction of AI-driven emotional data. In contrast to traditional branding concepts, this study indicates that AI can suggest dynamic and emotionally resonant brand identities for artists. The real time audience response gives proper guidance for the decision-making. This study enriches the knowledge of AI’s applicability to branding processes in the context of the music industry and opens the possibilities for additional advancements in building emotionally appealing brand identities.

A Visual Indoor Localization Method Based on Efficient Image Retrieval

The task of indoor visual localization, utilizing camera visual information for user pose calculation, was a core component of Augmented Reality (AR) and Simultaneous Localization and Mapping (SLAM). Existing indoor localization technologies generally used scene-specific 3D representations or were trained on specific datasets, making it challenging to balance accuracy and cost when applied to new scenes. Addressing this issue, this paper proposed a universal indoor visual localization method based on efficient image retrieval. Initially, a Multi-Layer Perceptron (MLP) was employed to aggregate features from intermediate layers of a convolutional neural network, obtaining a global representation of the image. This approach ensured accurate and rapid retrieval of reference images. Subsequently, a new mechanism using Random Sample Consensus (RANSAC) was designed to resolve relative pose ambiguity caused by the essential matrix decomposition based on the five-point method. Finally, the absolute pose of the queried user image was computed, thereby achieving indoor user pose estimation. The proposed indoor localization method was characterized by its simplicity, flexibility, and excellent cross-scene generalization. Experimental results demonstrated a positioning error of 0.09 m and 2.14° on the 7Scenes dataset, and 0.15 m and 6.37° on the 12Scenes dataset. These results convincingly illustrated the outstanding performance of the proposed indoor localization method.

A Cover-Independent Deep Image Hiding Method Based on Domain Attention Mechanism

Recently,deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information hiding.However,these approaches have some limitations.For example,a cover image lacks self-adaptability,information leakage,or weak concealment.To address these issues,this study proposes a universal and adaptable image-hiding method.First,a domain attention mechanism is designed by combining the Atrous convolution,which makes better use of the relationship between the secret image domain and the cover image domain.Second,to improve perceived human similarity,perceptual loss is incorporated into the training process.The experimental results are promising,with the proposed method achieving an average pixel discrepancy(APD)of 1.83 and a peak signal-to-noise ratio(PSNR)value of 40.72 dB between the cover and stego images,indicative of its high-quality output.Furthermore,the structural similarity index measure(SSIM)reaches 0.985 while the learned perceptual image patch similarity(LPIPS)remarkably registers at 0.0001.Moreover,self-testing and cross-experiments demonstrate the model’s adaptability and generalization in unknown hidden spaces,making it suitable for diverse computer vision tasks.

A chaotic hierarchical encryption/watermark embedding scheme for multi-medical images based on row-column confusion and closed-loop bi-directional diffusion

Security during remote transmission has been an important concern for researchers in recent years.In this paper,a hierarchical encryption multi-image encryption scheme for people with different security levels is designed,and a multiimage encryption(MIE)algorithm with row and column confusion and closed-loop bi-directional diffusion is adopted in the paper.While ensuring secure communication of medical image information,people with different security levels have different levels of decryption keys,and differentiated visual effects can be obtained by using the strong sensitivity of chaotic keys.The highest security level can obtain decrypted images without watermarks,and at the same time,patient information and copyright attribution can be verified by obtaining watermark images.The experimental results show that the scheme is sufficiently secure as an MIE scheme with visualized differences and the encryption and decryption efficiency is significantly improved compared to other works.

Visually meaningful image encryption algorithm based on digital signature

Traditional image encryption algorithms transform a plain image into a noise-like image.To lower the chances for the encrypted image being detected by the attacker during the image transmission,a visually meaningful image encryption scheme is suggested to hide the encrypted image using another carrier image.This paper proposes a visually meaningful encrypted image algorithm that hides a secret image and a digital signature which provides authenticity and confidentiality.The recovered digital signature is used for the purpose of identity authentication while the secret image is encrypted to protect its confidentiality.Least Significant Bit(LSB)method to embed signature on the encrypted image and Lifting Wavelet Transform(LWT)to generate a visually meaningful encrypted image are designed.The proposed algorithm has a keyspace of 139.5-bit,a Normalized Correlation(NC)value of 0.9998 which is closer to 1 and a Peak Signal to Noise Ratio(PSNR)with a value greater than 50 dB.Different analyses are also performed on the proposed algorithm using different images.The experimental results show that the proposed scheme is with high key sensitivity and strong robustness against pepper and salt attack and cropping attack.Moreover,the histogram analysis shows that the original carrier image and the final visual image are very similar.

Red Deer Optimization with Artificial Intelligence Enabled Image Captioning System for Visually Impaired People

The problem of producing a natural language description of an image for describing the visual content has gained more attention in natural language processing(NLP)and computer vision(CV).It can be driven by applications like image retrieval or indexing,virtual assistants,image understanding,and support of visually impaired people(VIP).Though the VIP uses other senses,touch and hearing,for recognizing objects and events,the quality of life of those persons is lower than the standard level.Automatic Image captioning generates captions that will be read loudly to the VIP,thereby realizing matters happening around them.This article introduces a Red Deer Optimization with Artificial Intelligence Enabled Image Captioning System(RDOAI-ICS)for Visually Impaired People.The presented RDOAI-ICS technique aids in generating image captions for VIPs.The presented RDOAIICS technique utilizes a neural architectural search network(NASNet)model to produce image representations.Besides,the RDOAI-ICS technique uses the radial basis function neural network(RBFNN)method to generate a textual description.To enhance the performance of the RDOAI-ICS method,the parameter optimization process takes place using the RDO algorithm for NasNet and the butterfly optimization algorithm(BOA)for the RBFNN model,showing the novelty of the work.The experimental evaluation of the RDOAI-ICS method can be tested using a benchmark dataset.The outcomes show the enhancements of the RDOAI-ICS method over other recent Image captioning approaches.

Deep learning-based automated grading of visual impairment in cataract patients using fundus images

Cataract is the leading cause of visual impairment globally.The scarcity and uneven distribution of ophthalmologists seriously hinder early visual impairment grading for cataract patients in the clin-ic.In this study,a deep learning-based automated grading system of visual impairment in cataract patients is proposed using a multi-scale efficient channel attention convolutional neural network(MECA_CNN).First,the efficient channel attention mechanism is applied in the MECA_CNN to extract multi-scale features of fundus images,which can effectively focus on lesion-related regions.Then,the asymmetric convolutional modules are embedded in the residual unit to reduce the infor-mation loss of fine-grained features in fundus images.In addition,the asymmetric loss function is applied to address the problem of a higher false-negative rate and weak generalization ability caused by the imbalanced dataset.A total of 7299 fundus images derived from two clinical centers are em-ployed to develop and evaluate the MECA_CNN for identifying mild visual impairment caused by cataract(MVICC),moderate to severe visual impairment caused by cataract(MSVICC),and nor-mal sample.The experimental results demonstrate that the MECA_CNN provides clinically meaning-ful performance for visual impairment grading in the internal test dataset:MVICC(accuracy,sensi-tivity,and specificity;91.3%,89.9%,and 92%),MSVICC(93.2%,78.5%,and 96.7%),and normal sample(98.1%,98.0%,and 98.1%).The comparable performance in the external test dataset is achieved,further verifying the effectiveness and generalizability of the MECA_CNN model.This study provides a deep learning-based practical system for the automated grading of visu-al impairment in cataract patients,facilitating the formulation of treatment strategies in a timely man-ner and improving patients’vision prognosis.

Aristotelian Semantics, Homo Economicus, Images, and Brands

Aristotle＇s general theory of meaning is describing for the first time relations among linguistic signs, mental images, and real things. Centuries later, the triangle of meaning or the semiotic triangle became a model of how objects interact with signs and interpreters （C. S. Peirce） or how linguistic symbols are related to the objects they represent （Ogden and Richards 1923）. However, these triangles can be traced back to the 4th century BC, in Aristotle＇s Organon, when it was first mentioned the importance of images and signs in the creation of meaning. The nature of universals as mental images and their relation to the objects is still debated and, recently Lambert Wiesing＇s The Philosophy of Perception challenges current theories of perception. Taking perception to be real is in the core of the new debates about concept of mind. What the reality means for a subject is a central philosophical question （Meztinger, The Ego tunnel）. The new triangle of meaning is not only a relation among objects, realities, signs but a relation among real, objectified entities, irrespective if they are in the mind or outside it. In this new approach, the question of how human perception is possible is reformulated by questions about what perception induces us to be and do. Perceptions are embodied, to be visible, and to continually participate in the public and physical world we perceive. Looking back to Aristotle＇s work from these new approaches our paper argues that Aristotelian images were conceived by him as entities strongly related to action. As mind perceptions which determine us to act, they do not have a passive role but rather taking the lead in our life. This is very much in line with modem philosophical thinking. His thoughts about images and dynamics of reality based on perception and images had important consequences in economics, marketing and branding, giving to perceptions an active role in turning potential reality in actual reality. Brands are in fact images and perceptions in action and interaction and are built in order to compel us to act either to influence or to be influenced.

The Balance Between the Transmitted and the Perceived Image of Luxury Fragrance Brands

The luxury market has experienced considerable growth over recent years, being one of the sectors that have been the most resistant to the current economic recession. Selective fragrances make up one of the primary categories of the so-called accessible luxury consumed by a middle class that is seeking to approach the upper classes by copying their lifestyle. Despite the importance of this market, there is relatively little literature existing in regards to the study of the image of luxury brands due to the complexity of the luxury phenomenon. This article presents the results of an initial qualitative study conducted on focus groups of luxury fragrance consumers, making it possible to identify the types of attributes to be considered when studying the brand image of said luxury products. Subsequently, a quantitative study was conducted in order to determine the perceived image of the principle luxury fragrance brands by consumers. Thanks to this study, it has been possible to determine the typical profile of each of the analyzed brands so that a subsequent comparison may be made with the advertising created by said brands in order to verify whether or not the image projected in their advertising corresponds with the perceived image of their target audience.

Visual Basic.NET环境下存取数据库的Image字段数据

本文主要讲解在Visual Basic．NET中对数据库中特殊数据处理的一般方法，以帮助大家了解Imag字段的存取步骤和常用控件。

Visual Basic中处理SQL Server 2005的image型数据的方法

SQL Server 2005的image型数据不能通过INSERT和UPDATE等语句进行插入和更新,这给处理image型数据带来十分不便。讨论了在Visual Basic中处理SQL Server 2005的image型数据的一般方法,即利用ADO数据对象的Fields集合的AppendChunk方法和GetChunk方法及ADO Data控件进行数据的填充和读取。

Realizing precision pulse TIG welding with arc length control and visual image sensing based weld detection

Methods of arc length control and visual image based weld detection for precision pulse TIG welding were investigated. With a particular all hardware circuit, arc voltage during peak current stage is sampled and integrated to indicate arc length, deviation of arc length and adjusting parameters are calculated and output to drive a step motor directly. According to the features of welding image grabbed with CCD camera, a special algorithm was developed to detect the central line of weld fast and accurately. Then an application system were established, whose static arc length error is ±0.1 mm with 20 A average current and 1 mm given arc length, static detection precision of weld is 0.01 mm , processing time of each image is less than 120 ms . Precision pulse TIG welding of some given thin stainless steel components with complicated curved surface was successfully realized.

Adaptive image enhancement algorithm based on fuzzy entropy and human visual characteristics

To overcome the shortcomings of the Lee image enhancement algorithm and its improvement based on the logarithmic image processing(LIP) model, this paper proposes what we believe to be an effective image enhancement algorithm. This algorithm introduces fuzzy entropy, makes full use of neighborhood information, fuzzy information and human visual characteristics.To enhance an image, this paper first carries out the reasonable fuzzy-3 partition of its histogram into the dark region, intermediate region and bright region. It then extracts the statistical characteristics of the three regions and adaptively selects the parameter αaccording to the statistical characteristics of the image’s gray-scale values. It also adds a useful nonlinear transform, thus increasing the ubiquity of the algorithm. Finally, the causes for the gray-scale value overcorrection that occurs in the traditional image enhancement algorithms are analyzed and their solutions are proposed.The simulation results show that our image enhancement algorithm can effectively suppress the noise of an image, enhance its contrast and visual effect, sharpen its edge and adjust its dynamic range.

A Visual Cryptography Based Digital Image Copyright Protection

A method for creating digital image copyright protection is proposed in this paper. The proposed method in this paper is based on visual cryptography defined by Noor and Shamir. The proposed method is working on selection of random pixels from the original digital image instead of specific selection of pixels. The new method proposed does not require that the watermark pattern to be embedded in to the original digital image. Instead of that, verification information is generated which will be used to verify the ownership of the image. This leaves the marked image equal to the original image. The method is based on the relationship between randomly selected pixels and their 8-neighbors’ pixels. This relationship keeps the marked image coherent against diverse attacks even if the most significant bits of randomly selected pixels have been changed by attacker as we will see later in this paper. Experimental results show the proposed method can recover the watermark pattern from the marked image even if major changes are made to the original digital image.

An image mosaic technique with non-overlapping regions based on microscopic vision in precision assembly

Microscopic vision has been widely applied in precision assembly.To achieve sufficiently high resolution in measurements for precision assembly when the sizes of the parts involved exceed the field of view of the vision system,an image mosaic technique must be used.In this paper,a method for constructing an image mosaic with non-overlapping areas with enhanced efficiency is proposed.First,an image mosaic model for the part is created using a geometric model of the measurement system installed on a X-Y-Z precision stages with high repeatability,and a path for image acquisition is established.Second,images are captured along the same path for a specified calibration plate,and an entire image is formed based on the given model.The measurement results obtained from the specified calibration plate are utilized to identify mosaic errors and apply compensation for the part requiring measurement.Experimental results show that the maximum error is less than 4μm for a camera with pixel equivalent 2.46μm,thereby demonstrating the accuracy of the proposed method.This image mosaic technique with non-overlapping regions can simplify image acquisition and reduce the workload involved in constructing an image mosaic.

In vivo imaging reveals a synchronized correlation among neurotransmitter dynamics during propofol and sevoflurane anesthesia

General anesthesia is widely applied in clinical practice.However,the precise mechanism of loss of consciousness induced by general anesthetics remains unknown.Here,we measured the dynamics of five neurotransmitters,includingγ-aminobutyric acid,glutamate,norepinephrine,acetylcholine,and dopamine,in the medial prefrontal cortex and primary visual cortex of C57BL/6 mice through in vivo fiber photometry and genetically encoded neurotransmitter sensors under anesthesia to reveal the mechanism of general anesthesia from a neurotransmitter perspective.Results revealed that the concentrations of γ-aminobutyric acid,glutamate,norepinephrine,and acetylcholine increased in the cortex during propofol-induced loss of consciousness.Dopamine levels did not change following the hypnotic dose of propofol but increased significantly following surgical doses of propofol anesthesia.Notably,the concentrations of the five neurotransmitters generally decreased during sevoflurane-induced loss of consciousness.Furthermore,the neurotransmitter dynamic networks were not synchronized in the non-anesthesia groups but were highly synchronized in the anesthetic groups.These findings suggest that neurotransmitter dynamic network synchronization may cause anesthetic-induced loss of consciousness.