Comparative Study on Person Re-identification Using Color and Shape Features-Based Body Part Matching

Plant disease is main reason of agricultural crops production losses. Leaf disease in plant occurs due to fungai, virus and bacterias. Image contains various important features which is used in classification. In this paper author initially detect disease then classify disease using extracted features. It takes five diseased leaves (Black rot, Black Measles, Leaf blight, Septoria leaf spot, Bacterial spot) and healthy leaf images then identify leaf is diseased or healthy then if leaf is diseased then classify type of disease. Color features mean, standard deviation, skewness and kurtosis computed then Region based shape feature calculated to identify the size of spots. Texture feature calculated using gray level co-occurrence matrix (GLCM) which identifies texture of image using distance and 45° angle variation in GLCM. Extracted features sent to trained feed forward neural network and classify diseased with color, shape and texture feature individually and combination of all features then observe that combination of color, shape and texture feature improve the performance of classification accuracy.

Soil nutrients are commonly heterogeneously distributed at different spatial scales. Although numerous studies have tested the effects of soil nutrient heterogeneity on growth of clonal plants producing either spreading ramets or clumping ramets, no study has examined the effects on the growth of clonal plants producing both spreading and clumping ramets and how spatial scale affects such effects. To test these effects, clones of Buchloe dactyloides, a stoloniferous clonal plant that produces both clumping and spreading ramets, were grown in six heterogeneous environments with different patch sizes and one homogeneous environment containing the same quantity of nutrients. Total biomass, total number of ramets, number of clumping ramets, number of spreading ramets, spacer length, or root:shoot ratio of the whole plants did not differ significantly among the seven treatments. However, at the patch level there were significant effects of patch size by nutrient level on biomass, number of ramets, number of spreading ramets, and number of clumping ramets, and these four variables were significantly larger in the nutrient-rich patches than in the nutrient-poor patches in the heterogeneous treatment with the largest patch size, but not in the other five heterogeneous treatments with smaller patch sizes. Neither nutrient level nor patch size significantly affected spacer length or root:shoot ratio. Based on our results, we propose that B. dactyloides can efficiently exploit nutrient-rich patches by a plastic response of clumping ramets and spreading ramets at larger spatial scales of soil heterogeneity but not at smaller ones.

Recently, the person re-identification task becomes increasingly crucial in crowded scenarios, e.g., airports and schools. Many methods with high performance have been proposed to solve this problem. However, the existence of occlusion still challenges the development of person re-identification. In this work, we present the novel Pose - Guided Mixed Attention Network (PGMANet), an end-to-end framework to deal with pedestrian reidentification under occluded situations by fusing posture and second-order information. Specially, we employ two models. The first is Human Part - level Attention Model. We use key point information of a pedestrian to generate a heat map to enhance the pedestrian body part's feature. Simultaneously, we design Second - order Information Attention Model to investigate the correlation among features of different parts. Experimental results show that our method achieves state-of-the-art person re-identification performance on two challenging occlusion datasets Occluded-DukeMTMC and Occluded-Reid.

Person re-identification (re-ID) as a retrieval task often utilizes a re-ranking model to improve performance. Existing re-ranking methods are typically designed for conventional person re-ID with RGB images, while skeleton representation re-ranking for skeleton-based person re-ID still remains to be explored. To fill this gap, we revisit the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$k$</tex-math></inline-formula> -reciprocal distance re-ranking model in this letter, and propose a generic re-ranking method that exploits the salient skeleton features to perform <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$k$</tex-math></inline-formula> -reciprocal distance encoding for skeleton-based person re-ID re-ranking. In particular, we devise the skeleton sequence pooling to aggregate the most salient features of skeletons within a sequence, and combine both original Euclidean distance and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$k$</tex-math></inline-formula> -reciprocal distance to re-rank the skeleton sequence representations for person re-ID. Furthermore, we propose the context-based Rank-1 voting that jointly exploits the initial ranking list and re-ranking list to vote for the top candidate to enhance the Rank-1 matching. Extensive experiments on three public benchmarks demonstrate that our approach can effectively re-rank different state-of-the-art skeleton representations and significantly improve their person re-ID performance.

A robust method is proposed in this paper to retrieve digital images using combination of color, texture and shape features. The proposed method consists of three stages. Shape detection is done based on TopHat transform to detect and crop object part of the image in the first stage. The second is included a texture feature extraction algorithm using color local binary patterns (CLBP) and local variance features together. Finally, to retrieve mostly closing matching images to the query, log likelihood ratio is used as non-similarity ratio. The performance of the proposed approach is evaluated using Corel and Simplicity image sets and it compared by some of other well-known approaches in terms of precision and recall which shows the superiority of the proposed approach. Shift invariant, Low noise sensitivity, rotation invariant are some of other advantages.

To improve the accuracy of person re-identification and reduce the size of models, a lightweight and accurate (LWA) unsupervised method is proposed. Firstly, a lightweight image classifier (LWC) is proposed. It combines DenseNet's convolutional layer and batch normalization layer to simplify its model structure. Then the spatio-temporal information of datasets is added to form a powerful classifier. Secondly, an optimization learning algorithm is proposed. A feeble classifier (LWB) is implemented by constructing a binary network. For the training of the network, the ranking information of a powerful classifier is used to enhance the recognition capability of the LWB. Furthermore, spatio-temporal information of datasets is added again to construct LWA classifier. The results show that the model size of LWB is about 80% smaller than that of the Siamese network model on the CUHK01 and VIPeR datasets. At the same time, the recognition accuracy of the LWA classifier is slightly improved on the Market-1501 and DukeMTMC target datasets.

Person re-identification (ReID) is to identify the same person across non-overlapping camera views. After a decade of development, the methods based on deep networks have achieved high performance on benchmarks and become mainstream. In applications, the features of gallery images extracted by deep learning-based methods are stored to speed up the query process and protect the sensitive information contained in the images. Unfortunately, it is demonstrated that turning the images into features cannot properly protect privacy, as these features could be reversed to the corresponding images, revealing the sensitive information they contain. Therefore, for preventing privacy leakage, recent methods learn their features against some feature reversal methods, and most conventional reversal methods focus on minimizing the difference between a reconstruction and its original image. However, there could be many reasonable reconstruction results from a single feature, and the conventional reversal methods will inevitably generate reconstruction results that lie in a different distribution from one of the original images, which cannot properly assess the private information for learning to protect and thus hamper the privacy-protected feature learning. To mitigate this problem, we enforce the reconstructions to follow the same distribution as the original images by the generative adversarial network (GAN). We operate this GAN-based feature reversal module accompanied by the conventional ReID feature extraction module and form a novel GAN-based feature privacy-protected person ReID model, which is expected to protect feature privacy so as against reversal attack and maintain ReID utility. We demonstrate that optimizing ReID model to accommodate privacy protection faces a double adversarial objective and is thus challenging. As a remedy, we design a novel two-step training and lazy update strategy that alternatively optimizes the feature extraction module and stabilizes the update process of the GAN-based feature reversal module. To evaluate the efficiency of the model in balancing its ReID utility and feature privacy protection, we introduce a novel metric called utility-reversibility ratio (URR). Compared with existing privacy-protected feature extraction models, the proposed method achieves a better balance between privacy protection and person ReID performance. Extensive experiments validate that our model can effectively protect feature privacy at a tiny accuracy cost, and validate the effectiveness of our model with the emerging diffusion model.

Person re-identification (re-ID) is a promising computer vision task. State-of-the-art methods mainly utilize deep learning based approaches to learn visual features for describing person appearances. Due to occlusion, complex background, different postures and light intensity, the technology faces many challenges. In this paper, a person re-identification method is proposed combining mask guiding and part pooling. First, person mask is generated by a segmentation sub-net, combining Macro-Micro Adversarial Network (MMAN) with Fully Convolution Networks (FCN). To alleviate the influence of background, a mask guiding strategy is designed integrating the mask with person feature map. Then a part pooling strategy is employed to extract local features of the person. The final loss function of the network is defined as the combination of global loss and local loss, which can describe the person in a comprehensive manner. Four public datasets are employed to test the performance of the proposed method. Our method achieves rank-1/mAP of 89.05%/72.83% on the Market-1501, 79.03%/62.06% on the DukeMTMC-reID, 46.79%/29.61% on the MSMT-17, 49.50%/45.03% on the CUHK03-NP. Experimental results show that the designed mask guiding and part pooling strategies can improve person re-ID performance.

Towards fast and kernelized orthogonal discriminant analysis on person re-identification

Deep learning-based person re-identification methods: A survey and outlook of recent works

In recent years, with the development of feature extraction and metric learning of deep neural network, the performance of person re-identification (Re-ID) based on deep learning has been greatly improved. However, the vulnerability of deep neural network is also affecting the security of person Re-ID model, and the adversarial examples become a common way to attack the deep models. In this paper, we propose a targeted adversarial attack method against person Re-ID by adding imperceptible noise on the query examples for the generation of adversarial examples, so that the retrieval results of query examples returned from the model are consistently biased towards the specific pedestrian. To test the effectiveness of the proposed method, several experiments are conducted on the Market-1501 dataset, and the results show that the targeted adversarial attack method can effectively attack the retrieval results of person Re-ID model.

As a fundamental task in automated video surveillance, person re-identification, which has received increasing attention in recent years, aims to match people across non-overlapping camera views in a multi-camera surveillance system. It has been reported that KISS metric learning has been followed by most of the previous supervised work because of its state of the art performance for person re-identification on VIPeR dataset. However, given only a small number of labeled image pairs available for training, the matching model certainly suffers from unstable learning process and poor matching result. To address this serious practical issue, we proposed a novel semi-supervised KISS metric learning (SS-KISS) approach which makes use of unlabeled data to improve the re-identification performance by 1) combining both global and local information to select the most confident image pairs from the unlabeled data; 2) using an ensemble approach, which explores advantages of supervised and unsupervised learning by reconciling two matching models on which labeled and un-labeled data to an optimal one via smart weighting schema. Extensive experiments have been conducted on three datasets: VIPeR, ETHZ, and i-LiDS, experimental results demonstrate that our approach achieves a sound performance in the case of small amount of labeled data.

Matching people in different camera views, commonly referred to as person re-identification, is an inherently challenging task due to the appearance disparity caused by view change.Other factors such as low image resolution and occlusion further compound this problem. As a highly demanded technique, person re-identification has been actively studied in recent years. Most of the existing approaches either focus on feature design or distance metric learning, based on appearance features. However, due to the view change, the appearance features may significantly vary for the same subject, resulting in matching difficulties. Instead of using features from a single modality, i.e, appearance, we propose to use multimodal features to improve the re-identification accuracy. Specifically, in this work, we leverage both appearance features and soft biometrics, i.e, human characteristics such as gender, to match individuals across cameras. We build multiple graphs, each of which represent one feature modality, and the graphs are then combined and optimized to derive the similarities between a probe and the gallery subjects. The proposed method is evaluated on the VIPeR dataset with annotated soft biometric labels. The results suggest that using multimodal features, e.g, appearance and soft biometrics, can improve the matching accuracy as compared to using appearance features only, and superior performance is obtained as compared to other state-of-the-art approaches.

In recent years, person reidentification has received growing attention with the increasing popularity of intelligent video surveillance. This is because person reidentification is critical for human tracking with multiple cameras. Recently, keep it simple and straightforward (KISS) metric learning has been regarded as a top level algorithm for person reidentification. The covariance matrices of KISS are estimated by maximum likelihood (ML) estimation. It is known that discriminative learning based on the minimum classification error (MCE) is more reliable than classical ML estimation with the increasing of the number of training samples. When considering a small sample size problem, direct MCE KISS does not work well, because of the estimate error of small eigenvalues. Therefore, we further introduce the smoothing technique to improve the estimates of the small eigenvalues of a covariance matrix. Our new scheme is termed the minimum classification error-KISS (MCE-KISS). We conduct thorough validation experiments on the VIPeR and ETHZ datasets, which demonstrate the robustness and effectiveness of MCE-KISS for person reidentification.

Person reidentification has attracted extensive research efforts in recent years. It is challenging due to the varied visual appearance from illumination, view angle, background, and possible occlusions, leading to the difficulties when measuring the relevance, i.e., similarities, between probe and gallery images. Existing methods mainly focus on pairwise distance metric learning for person reidentification. In practice, pairwise image matching may limit the data for comparison (just the probe and one gallery subject) and yet lead to suboptimal results. The correlation among gallery data can be also helpful for the person reidentification task. In this paper, we propose to investigate the high-order correlation among the probe and gallery data, not the pairwise matching, to jointly learn the relevance of gallery data to the probe. Recalling recent progresses on feature representation in person reidentification, it is difficult to select the best feature and each type of feature can benefit person description from different aspects. Under such circumstances, we propose a multihypergraph joint learning algorithm to learn the relevance in corporation with multiple features of the imaging data. More specifically, one hypergraph is constructed using one type of feature and multiple hypergraphs can be generated accordingly. Then, the learning process is conducted on the multihypergraph structure, and the identity of a probe is determined by its relevance to each gallery data. The merit of the proposed scheme is twofold. First, different from pairwise image matching, the proposed method jointly explores the relationships among different images. Second, multimodal data, i.e., different features, can be formulated in the multihypergraph structure, which can convey more information in the learning process and can be easily extended. We note that the proposed method is a general framework to incorporate with any combination of features, and thus is flexible in practice. Experimental results and comparisons with the state-of-the-art methods on three public benchmarking data sets demonstrate the superiority of the proposed method.