Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study

Quality is a very important parameter for all objects and their functionalities. In image-based object recognition, image quality is a prime criterion. For authentic image quality evaluation, ground truth is required. But in practice, it is very difficult to find the ground truth. Usually, image quality is being assessed by full reference metrics, like MSE (Mean Square Error) and PSNR (Peak Signal to Noise Ratio). In contrast to MSE and PSNR, recently, two more full reference metrics SSIM (Structured Similarity Indexing Method) and FSIM (Feature Similarity Indexing Method) are developed with a view to compare the structural and feature similarity measures between restored and original objects on the basis of perception. This paper is mainly stressed on comparing different image quality metrics to give a comprehensive view. Experimentation with these metrics using benchmark images is performed through denoising for different noise concentrations. All metrics have given consistent results. However, from representation perspective, SSIM and FSIM are normalized, but MSE and PSNR are not;and from semantic perspective, MSE and PSNR are giving only absolute error;on the other hand, SSIM and PSNR are giving perception and saliency-based error. So, SSIM and FSIM can be treated more understandable than the MSE and PSNR.

Lung Cancer Detection Using CT Image Based on 3D Convolutional Neural Network

Early detection of lung nodule is of great importance for the successful diagnosis and treatment of lung cancer. Many researchers have tried with diverse methods, such as thresholding, computer-aided diagnosis system, pattern recognition technique, backpropagation algorithm, etc. Recently, convolutional neural network (CNN) finds promising applications in many areas. In this research, we investigated 3D CNN to detect early lung cancer using LUNA 16 dataset. At first, we preprocessed raw image using thresholding technique. Then we used Vanilla 3D CNN classifier to determine whether the image is cancerous or non-cancerous. The experimental results show that the proposed method can achieve a detection accuracy of about 80% and it is a satisfactory performance compared to the existing technique.

An Efficient Disease Detection Technique of Rice Leaf Using AlexNet

As nearly half of the people in the world live on rice, so the rice leaf disease detection is very important for our agricultural sector. Many researchers worked on this problem and they achieved different results according to their applied techniques. In this paper, we applied AlexNet technique to detect the three prevalence rice leaf diseases termed as bacterial blight, brown spot as well as leaf smut and got a remarkable outcome rather than the previous works. AlexNet is a special type of classification technique of deep learning. This paper shows more than 99% accuracy due to adjusting an efficient technique and image augmentation.

Multiple Image Watermarking with Discrete Cosine Transform

Multiple image watermarking is an advanced concept of singular watermarking techniques. The existing singular digital image watermarking techniques cannot obtain all the design goals, such as imperceptibility, robustness, security, and capacity simultaneously with perfection. Hence, the multiple image watermarking technique is designed that embeds several watermarks into the same host image for conveying multiple information. This paper proposed a multiple image watermarking technique with Discrete Cosine Transform (DCT) for ensuring the low computational time for embedding, encryption, decryption as well as extraction of the watermark images. Here, DCT is used to ensure the visual quality of the host image, and a random binary matrix is used to improve the security of the digital image. We have given a basic framework for multiple image watermarking. Our experimental results show satisfactory performance.

Single Image Dehazing: An Analysis on Generative Adversarial Network

Haze is a very common phenomenon that degrades or reduces visibility. It causes various problems where high-quality images are required such as traffic and security monitoring. So haze removal from scenes is an immediate demand for clear vision. Recently, in addition to the conventional dehazing mechanisms, different types of deep generative adversarial networks (GAN) are applied to suppress the noise and improve the dehazing performance. But it is unclear how these algorithms would perform on hazy images acquired “in the wild” and how we could gauge the progress in the field. To bridge this gap, this presents a comprehensive study on three single image dehazing state-of-the-art GAN models, such as AOD-Net, cGAN, and DHSGAN. We have experimented using benchmark dataset consisting of both synthetic and real-world hazy images. The obtained results are evaluated both quantitatively and qualitatively. Among these techniques, the DHSGAN gives the best performance.

Analysis of a Conceptual Model and Assessment of the e-Procurement System in Bangladesh

The public procurement system in Bangladesh has been running by traditional manual process under the flagship of Public Procurement Act (PPA 2006) and Public Procurement Rules (PPR 2008). Public procurement agencies have been facing challenges in this manual tendering system. To overcome this problem and to bring reality to the “Digital Bangladesh” slogan, the Government of Bangladesh introduced the e-Procurement system under the e-GP (Electronic Government Procurement) guideline 2011. After the inception of e-procurement, there is no e-procurement assessment model to improve the e-GP system. The purpose of this research is to develop a conceptual framework and to design an e-procurement assessment model. With this view, we have considered one of the biggest entity Roads and Highways Department (RHD) of the Government of Bangladesh, for field study. Mixed methods along with FGD (Focus Group Discussion), KII (Key Informant Interview), and survey questionnaires are used to collect data from RHD, and then Statistical Package for Social Science (SPSS) software is used for regression analysis and hypothesis testing to develop the e-Procurement assessment model. The novel contribution of the study lies in the test of the hypothesis that focuses on developing the conceptual model of the e-procurement assessment system in Bangladesh. Findings of the study are essential for all Procurement Entity (PE) and suppliers i.e. contractors of RHD who are engaged in the construction of the infrastructure project development project.

A Survey on Matching of Shoeprint with Reference Footwear in Forensic Study

Footwear impression marks on the outside surface of shoes are distinctive patterns and an important forensic clue often found at offense scenes. However, in many cases, the footwear mark is treated with improper evidence due to difficulties in visibility and understanding. This paper presents a thorough review of matching algorithms along with enhancement techniques of shoeprint in the forensic study. Finally, it shows some research directions.

Simulation of Hazy Image and Validation of Haze Removal Technique

Haze hampers the performance of vision systems. So, removal of haze appearance in a scene should be the first-priority for clear vision. It finds wide spectrum of practical applications. A good number of dehazing techniques have already been developed. However, validation with the help of ground truth i.e. simulated haze on a clear image is an ultimate necessity. To address this issue, in this work synthetic haze images with various haze concentrations are simulated and then used to confirm the validation task of dark-channel dehazing mechanism, as it is a very promising single image dehazing technique. The simulated hazy image is developed using atmospheric model with and without Perlin noise. The effectiveness of dark-channel dehazing method is confirmed using the simulated haze images through average gradient metric, as haze reduces the gradient score.

Image-Based Vehicle Speed Estimation

Vehicle speed is an important parameter that finds tremendous application in traffic control identifying over speed vehicles with a view to reducing accidents. Many methods, such as using RADAR and LIDAR sensors have been proposed. However, these are expensive, and their accuracy is not quite satisfactory. In this paper, a video-based vehicle speed determination method is presented. The method shows satisfactory performance on standard data sets and gives that error rate of velocity estimation is within 10%.

Implementation and Analysis of an IoT-Based Home Automation Framework

The pervasive advancement in the field of an autonomous system is significantly influenced by the concept of integrating a large number of devices. The use Internet of Things (IoT) has increased day by day for making connected devices over the internet. Besides, mobile sensing devices operated by IoT including smartphones, tablets, digital cameras, sensors, etc. are providing access to a large variety of data and services based on human interaction. In this paper, the implementation and analysis of an IoT-based home automation framework using NodeMCU through the MQTT protocol are described. This helps the users to monitor and control home appliances from remote places by using a mobile application over the internet.

A Hybrid-Binarization Approach for Degraded Document Enhancement

Images get degraded because of unbalanced enlightenment including text-smearing, ink-bleeding, degradation of ink over time, manuscript characters from background coming out and blended with the characters of the main side etc. So, degraded-document enhancement is a challenging issue. In recent years, several binarization approaches are proposed to enhance these images. These techniques have focused on finding a suitable global threshold value or a local threshold value for every region to eliminate the degradations. A hybrid approach can be a good solution to deal with all these matters together. This paper proposes a hybrid approach of binarization for degraded documents to produce better quality result. Then, the performance of the proposed technique is evaluated using DIBCO 2010 to DIBCO 2018 databases and compared with the existing methods which confirmed that the proposed method is robust, efficient. Finally, a direction towards future works and challenges is stated.

Hybrid Methodologies for Segmentation and Classification of Skin Diseases: A Study

Skin disorders are a serious global health problem for humans. These disorders become dangerous when they grow into the malignant stage. Hence, it is necessary to detect these diseases at their early stage. A mobile-based automated skin disease detection system is vital for detecting skin diseases. This system also offers cure or treatment plans to the affected person through the short message service (SMS) or electronic mail (e-mail). An effective skin disease detection system consists of three processes: segmentation, feature extraction, and classification. Several hybrid methodologies are already developed for the above-mentioned processes for detecting skin diseases at the initial stage. This research gives a standard hybrid framework for detecting skin diseases and highlights some design requirements for achieving high accuracy. Existing state-of-the-art hybrid methods of three processes for detecting skin diseases along with their limitations are also summarized. It also identifies the challenges for developing an effective skin disease detection system and gives future research directions.

Comparing the Efficiency of Manual and Electronic Tender Document Preparation: Cost and Time Context

In Bangladesh, both manual and e-GP system is used to perform public procurement. Before tender publication, tender documents have to be prepared by the Procurement Entities (PEs). The problem is that the manual tendering system involves more cost and time in preparing tender documents. The study’s purpose is to compare now the efficiency of tender document preparation in the manual system with the e-GP system. This study tests the cost and time involved in tender document preparation, both manual and e-procurement tenders. Sample data was collected from the 11 RHD zones. Structured survey questionnaires were used to collect primary data from the PE officers of RHD. A hypothesis test was performed using the model of independent samples t-test. The test results indicated that e-Procurement tender document preparation costs and time were less than manual tendering. Academicians, researchers, PE officers, and policymakers will benefit from the study’s conclusions.

Comparing the Cost and Time of Tender Opening Committee Report Preparation for Manual and E-Procurement Tenders in the Roads and Highways Department of Bangladesh

Bangladesh’s public procurement system has been traditional, i.e., a manual tendering system, under the legislative guidance of PPA-2006 and PPR-2008. Manual tendering has long been a source of concern for public procurement agencies regarding tender opening related to cost and time. To resolve this challenge and make the dream of a Digital Bangladesh a reality, the Government of Bangladesh launched the e-Procurement system in 2011 under the flagship of e-GP Guidelines. Following the successful pilot testing conducted under the umbrella of the CPTU, all public PEs are attempting to implement electronic procurement tenders. This study aims to examine the cost and time involved in preparing Tender Opening Committee (TOC) Reports for manual and e-procurement tenders in Bangladesh’s Roads and Highways Department. A mixed-method was used to collect data from the population of 11 RHD zones, including KII and primarily survey questionnaires. The independent samples t-test was used to compare data and hypothesis tests from two groups using SPSS software. The results indicated that e-Procurement tendering, tender opening preparation costs and time were more efficient than manual tendering. Academicians, students, practitioners, researchers, and policymakers will benefit from the study’s conclusions. Additionally, the government will be urged to improve policies such as the PPA 2006, the PPR 2008, and the 2011 e-GP Guideline.