A novel sparse model based forensic writer identification

In computer vision, the bag-of-words (BoW) model has been widely applied to image related tasks, such as large scale image retrieval, image classification, and object categorization. The sparse coding (SC) method which leverages SC as a means of feature coding can guarantee both sparsity of coding vector and lower reconstruction error in the BoW model. Thus it can achieve better performance than the traditional vector quantization method. However, it suffers from the side effect introduced by the non-smooth sparsity regularizer that quite different words may be selected for similar patches to favor sparsity, resulting in the loss of correlation between the corresponding coding vectors. To address this problem, in this paper, we propose a novel soft assignment method based on index combination of top-2 large sparse codes of local descriptors to make the SC-based BoW tolerate the case of different word selection for similar patches. To further ensure similar patches select same words to generate similar coding vectors, we propose a collaborative dictionary learning method through imposing the sparse code similarity regularization factor along with the row sparsity regularization across data instances on top of group sparse coding. Experiments on the well-known public Oxford dataset demonstrate the effectiveness of our proposed methods.

Fast low rank representation based spatial pyramid matching for image classification

In this paper, we present a novel scheme for text-independent online writer identification. As a first contribution, we propose histogram based features, inspired from the area of object detection, to describe the structural primitives of handwriting. Secondly, we have used sparse coding techniques to learn prototypes, that describe the general writing characteristics of the authors. To the best of our knowledge, the present proposal is the first of its kind that exploits the sparse learning framework for online writer identification. In addition, we consider the inclusion of ideas from information retrieval into our sparse representation to formulate a novel descriptor for each document. The efficacy of our proposal is tested on the handwritten paragraphs and text lines of the IAM On-Line Handwriting Database. We also provide a quantitative comparison of performance of our histogram based features with Fourier and Wavelet descriptors. The results are promising.

Image classification is an important problem in computer vision. The sparse coding spatial pyramid matching (ScSPM) framework is widely used in this field. However, the sparse coding cannot effectively handle very large training sets because of its high computational complexity, and ignoring the mutual dependence among local features results in highly variable sparse codes even for similar features. To overcome the shortcomings of previous sparse coding algorithm, we present an image classification method, which replaces the sparse dictionary with a stable dictionary learned via low computational complexity clustering, more specifically, a k-medoids cluster method optimized by k-means++. The proposed method can reduce the learning complexity and improve the feature’s stability. In the experiments, we compared the effectiveness of our method with the existing ScSPM method and its improved versions. We evaluated our approach on two diverse datasets: Caltech-101 and UIUC-Sports. The results show that our method can increase the accuracy of spatial pyramid matching, which suggests that our method is capable of improving performance of sparse coding features.

The high dimensionality of hyperspectral images brings a heavy burden for image processing. Band selection is a common technique for dimensionality reduction. Since the labels of hyperspectral images are difficult to collect, a new semisupervised band selection method based on affinity propagation (AP) is proposed. AP, an exemplar-based clustering method, is famous due to fast execution time and low reconstruction error. For band selection, AP involves two key issues: band correlation and band preference. In this paper, a new normalized trivariable mutual information (normalized TMI, NTMI) is devised to measure band correlation for classification. NTMI considers not only band redundancy but also band synergy, and overcomes the sensitivity of TMI to the discriminative abilities of bands. Band preference is defined by the discriminative ability and informative amount of each band. Since the clustering methods are easily disturbed by noisy bands, a new statistical-based method for band correlation and band preference is devised. It can automatically remove noisy bands beforehand by exploiting the continuity property of bands. Finally, the proposed method can select highly discriminative and informative bands, and remove highly redundant bands. Experimental results on hyperspectral images demonstrate the effectiveness of the proposed semisupervised band selection method.

In recent years, sparse coding via dictionary learning has been widely used in many applications for exploiting sparsity patterns of data. For classification, useful sparsity patterns should have discrimination, which cannot be well achieved by standard sparse coding techniques. In this paper, we investigate structured sparse coding for obtaining discriminative class-specific group sparsity patterns in the context of classification. A structured dictionary learning approach for sparse coding is proposed by considering the \(\ell _{2,0}\) norm on each class of data. An efficient numerical algorithm with global convergence is developed for solving the related challenging \(\ell _{2,0}\) minimization problem. The learned dictionary is decomposed into class-specific dictionaries for the classification that is done according to the minimum reconstruction error among all the classes. For evaluation, the proposed method was applied to classifying both the synthetic data and real-world data. The experiments show the competitive performance of the proposed method in comparison with several existing discriminative sparse coding methods.

Sparse coding is a popular technique for achieving compact data representation and has been used in many applications. However, the instability issue often causes degeneration in practice and thus attracts a lot of studies. While the traditional graph sparse coding preserves the neighborhood structure of the data, this study integrates the low-rank representation(LRR) to fix the inconsistency of sparse coding by holding the subspace structures of the high-dimensional observations. The proposed method is dubbed low-rank graph regularized sparse coding (LogSC), which learns sparse codes and low-rank representations jointly rather than the traditional two-step approach. Since the two data representations share a dictionary matrix, the resulted sparse representation on this dictionary could be benefited from LRR. We solved the optimization problem of LogSC by using the linearized alternating direction method with adaptive penalty. Experimental results show the proposed method is discriminative in feature learning and robust to various noises. This work provides a one-step approach to integrating graph embedding in representation learning.

Teeth arrangement is essential in face ergonomics and healthiness. In addition, they play key roles in forensic medicine. Various computer-assisted procedures for medical application in quantitative dentistry require automatic classification and numbering of teeth in dental images. In this paper, we propose a multi-stage technique to classify teeth in multi-slice CT (MSCT) images. The proposed algorithm consists of the following three stages: segmentation, feature extraction and classification. We segment the teeth by employing several techniques including Otsu thresholding, morphological operations, panoramic re-sampling and variational level set. In the feature extraction stage, we follow a multi-resolution approach utilizing wavelet-Fourier descriptor (WFD) together with a centroid distance signature. We compute the feature vector of each tooth by employing the slice associated with largest tooth tissues. The feature vectors are employed for classification in the third stage. We perform teeth classification by a conventional supervised classifier. We employ a feed- forward neural network classifier to discriminate different teeth from each other. The performance of the proposed method was evaluated in the presence of 30 different MSCT data sets including 804 teeth. We compare classification results of the WFD technique with Fourier descriptor (FD) and wavelet descriptor (WD) techniques. We also investigate the invariance properties of the WFD technique. Experimental results reveal the effectiveness of the proposed method. We provided an integrated solution for teeth classification in multi-slice CT datasets. In this regard, suggested segmentation technique was successful to separate teeth from each other. The employed WFD approach was successful to discriminate and numbering of the teeth in the presence of missing teeth. The solution is independent of anatomical information such as knowing the sequence of teeth and the location of each tooth in the jaw.

A hierarchical latent topic model based on sparse coding

Airplane detection based on rotation invariant and sparse coding in remote sensing images

Hierarchical discriminating sparse coding for weak fault feature extraction of rolling bearings

The writer identification task infers the writer by analyzing the texture, structure, and other representative features of the handwriting. Inspired by the attention mechanism, an end-to-end writer identification model is proposed in this paper, which combines both global features and local features. The Vision Transformer is used as the backbone network, and the Convolutional block attention module (CBAM) is introduced to enhance the ability of global feature awareness of the model. The proposed method is evaluated on two public data sets, IAM and CVL respectively. In the task of word-level writer identification, the accuracy rates in two data sets were 90.1% and 92.3% respectively. In the task of page-level writer identification, the accuracy rates were 98.6% and 99.5%, as a state-of-the-art performance.

This paper presents a new activity-based person identification method using sparse coding and discriminative metric learning. Different from gait recognition where human walking activity is only utilized for person identification, we aim to recognize people from different activities such as running, jumping, skipping, and so on. For each activity video clip, we extract the binary human body mask using background substraction. Then, we cluster these body masks into a number of clusters by sparse coding with mean pooling to extract features for each video clip. Subsequently, we learn a discriminative distance metric under which intraclass (activities performed by the same person) variations are minimized and the interclass (activities performed by different persons) are maximized, simultaneously, such that more discriminative information can be exploited for recognition. Experimental results on a publicly available database are presented to show the efficacy of our proposed method.

Decomposing Strain Maps Using Fourier-Zernike Shape Descriptors

A new type of neural network for recognition tasks is presented in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN), is based on the forward only version of the counterpropagation network (CPN). The DSFPN, trains using a supervised algorithm and can grow dynamically during training, allowing subclasses in the training data to be learnt in an unsupervised manner. It is shown to train in times comparable to the CPN while giving better classification accuracies than the popular backpropagation network. Both Fourier descriptors and wavelet descriptors are used for image preprocessing and the wavelets are proven to give a far better performance.