Focusing on your subject:Deep subject-aware image composition recommendation networks

Photo composition is one of the most important factors in the aesthetics of photographs.As a popular application,composition recommendation for a photo focusing on a specific subject has been ignored by recent deep-learning-based composition recommendation approaches.In this paper,we propose a subject-aware image composition recommendation method,SAC-Net,which takes an RGB image and a binary subject window mask as input,and returns good compositions as crops containing the subject.Our model first determines candidate scores for all possible coarse cropping windows.The crops with high candidate scores are selected and further refined by regressing their corner points to generate the output recommended cropping windows.The final scores of the refined crops are predicted by a final score regression module.Unlike existing methods that need to preset several cropping windows,our network is able to automatically regress cropping windows with arbitrary aspect ratios and sizes.We propose novel stability losses for maximizing smoothness when changing cropping windows along with view changes.Experimental results show that our method outperforms state-of-the-art methods not only on the subject-aware image composition recommendation task,but also for general purpose composition recommendation.We also have designed a multistage labeling scheme so that a large amount of ranked pairs can be produced economically.We use this scheme to propose the first subject-aware composition dataset SACD,which contains 2777 images,and more than 5 million composition ranked pairs.The SACD dataset is publicly available at https://cg.cs.tsinghua.edu.cn/SACD/.

A leaf image localization based algorithm for different crops disease classification

Agricultural crop production is a major contributing element to any country’s economy.To maintain the economic growth of any country plants disease detection is a leading factor in agriculture.The contribution of the proposed algorithm is to optimize the extracted infor-mation from the available resources for the betterment of the result without any additional complexity.The proposed technique basically localizes the leaf region prior to the image classification into healthy and diseased.The novelty of this work is to fuse the information extracted from the available resources and optimize it to enhance the expected outcome.The leaf colors are analyzed using color transformation for the seed region identification.The mapping of a low-dimensional RGB color image into L*a*b color space provides an expansion of the spectral range.The neighboring pixels-based leaf region growing is applied on the initial seeds.In order to refine the leaf boundary and the disease-affected areas,we employed a random sample consensus(RANSAC)for suitable curve fitting.The feature sets using bag of visual words,Fisher vectors,and handcrafted features are extracted followed by classification using logistic regression,multilayer perceptron model,and support vector machine.The performance of the proposal is analyzed through PlantVillage datasets of apple,bell pepper,cherry,corn,grape,potato,and tomato.The simulation-based analysis of the proposed contextualization-based image categorization process outperforms as compared with the state of arts.The proposed approach provides average accuracy and area under the curve of 0.932 and 0.903,respectively.

Greenness identification based on HSV decision tree

Greenness identification from crop images captured outdoors is the important step for crop growth monitoring.The commonly used methods for greenness identification are based on visible spectral-index,such as the excess green index,the excess green minus excess red index,the vegetative index,the color index of vegetation extraction,the combined index.All these visible spectral-index based methods are working on the assumption that plants display a clear high degree of greenness,and soil is the only background element.In fact,the brightness and contrast of an image coming from outdoor environments are seriously affected by the weather conditions and the capture time.The color of the plant varies from dark green to bright green.The back ground elements may contain crop straw,straw ash besides soil.These environmental factors always make the visible spectral-index based methods unable to work correctly.In this paper,an HSV decision tree based method for greenness identification from maize seedling images captured outdoors is proposed.Firstly,the image was converted from RGB color space to HSV color space to avoid influence of illumination.Secondly,most of the background pixels were removed according to their hue values compared with the ones of green plants.Thirdly,the pixels of wheat straws whose hue values were intersected with tender green leaves were eliminated subject to their hues,saturations and values.At last,thresholding was employed to get the green plants.The results indicate that the proposed method can recognize greenness pixels correctly from the crop images captured outdoors.