Fusion of Multiple Features for Palmprint Authentication

In this paper, we propose a framework which fuses multiple features for action recognition in depth sequence. The fusion of multiple features is important for recognizing action since a single feature-based representation is inadequate to capture the variants. Hence, we use two types of features: i) a quantized vocabulary of local spatio-temporal descriptor HOG3D, and ii) a global projection based descriptor that computes the HOG from the Depth Motion Maps. To optimally combine these features, we input those features to different classifiers, where SVM is applied to estimate the probabilities of action labels. Then, we weight those probabilities respectively and sum it to find the maximum score of action labels. The proposed approach is tested on publicly available MSR Action3D dataset which demonstrates that fusion of multiple features help to achieve improved performance significantly, outperforming Li et al.[1] in most of the cases.

Feature fusion methods have been demonstrated to be effective for many computer vision based applications. These methods generally use multiple hand-crafted features. However, in recent days, features extracted through transfer leaning procedures have been proved to be robust than the hand-crafted features in myriad applications, such as object classification and recognition. The transfer learning is a highly appreciated strategy in deep convolutional neural networks (DCNNs) due to its multifaceted benefits. It heartens us to explore the effect of fusing multiple transfer learning features of different DCNN architectures. Thus, in this work, we extract features of image statistics by exploiting three different pre-trained DCNNs through transfer learning. Then, we transform the features into a generalized subspace through a recently introduced Autoencoder network and fuse them to form intra-class invariant feature vector that is used to train a multi-class Support Vector Machine (SVM). The experimental results on various datasets, including object and action image statistics show that the fusion of multiple transfer learning features improves classification accuracy as compared to fusion of multiple hand-crafted features and usage of single component transfer learning features.

Multiple depth-levels features fusion enhanced network for action recognition

Multiple color representation and fusion for diabetes mellitus diagnosis based on back tongue images

This paper presents an image segmentation method which utilizes image multiple features fusion, superpixel segmentation technique and hypergraph theory. Based on the image superpixel structure, our method maps each superpixel to a vertex and the similarity between two superpixels to an edge, to form a graph structure which can be represented as an affinity matrix. Hyperedges can be generated by doing spectral clustering on this affinity graph. Similarity of superpixels can be defined by different feature, then multiple features can be used to generate the hyperedges, and finally construct a hypergraph. Our approach uses the brightness, color and edge features. Then we use normalized hypergraph cut algorithm and the K-means clustering method to obtain the final segmentation result. The method was evaluated in Berkeley Segmentation Database. Experimental results show that our method can give better segmentations for the natural images. The computational efficiency and robustness of the method was verified through a comparative analysis of some state-of-the-art segmentation algorithms.KeywordsImage segmentationHypergraphSuperpixelMultiple features fusion

Multiple features data fusion method in color texture analysis

Feature fusion for basic behavior unit segmentation from video sequences

Palmprint is a very unique and distinctive biometric trait because of features such as a person's inimitable principal lines, wrinkles, delta points, and minutiae. These constitute the main reasons why palmprint verification is considered as one of the most reliable personal identification methods. However, a clear majority of the research on palm-prints are concentrated on 2-D palmprint images irrespective of the fact that the human palm is a 3D-surface. While 2-D palmprint recognition has proved to be efficient in terms of verification rate, it has some essential downsides. These restrictions can adversely affect the performance and robustness of the palmprint recognition system. One of the possible solutions to resolve the limitations associated with 2-D palm print authentication systems is (i) to use a 3-D scanning system and to produce high quality 3-D images with depth information; (ii) to map 3-D palm-print images into 2-D images which may support the usage of 3-D images with both biometric palmprint 2-D image databases and 2-D palmprint recognition tools. The bloom of 3-D technologies has made it easier to capture and store 3-D images. The problem of a direct mapping approach is that a large section of the palm is hard-pressed on the scanner surface during 2-D based acquisition. This paper proposes a novel technique to unravel/map 3-D palm images to its equivalent 2-D palm-print image. This image can be then used to perform efficient and accurate 2-D identification/ verification. Experimental results and discussions will also be presented.

This paper presents a robust face recognition algorithm by using transform domain-based multiple feature fusion and linear regression. Transform domain-based feature fusion can provide comprehensive face information for recognition, and decrease the effect of variations in illumination and pose. The holistic feature and local feature are extracted by discrete cosine transform and Gabor wavelet transform, respectively. Then the extracted holistic features and the local features are fused by weighted sum. The fused feature values are finally sent to linear regression classifier for recognition. The algorithm is evaluated on AR, ORL and Yale B face databases. Experiment results show that our proposed algorithm could be more robust than those single feature-based algorithms under pose and expression variations.

A 2D-based palmprint authentication system is easily fooled by spoof attacks, such as a fake palmprint. To solve that problem, we present a multifeature palmprint authentication system using both 2D and 3D palmprint features in this chapter. This chapter is organized as follows: Sect. 6.1 briefly introduces the background of 2D- and 3D-based palmprint authentication systems. Section 6.2 presents a multifeature palmprint authentication system and the 2D and 3D palmprint image acquisition device. In Sect. 6.3, 2D and 3D feature extraction algorithms are presented. In Sect. 6.4, we present a 2D features matching algorithm for 2D palmprint verification, and then present a 3D features matching algorithm for 3D palmprint authentication. Some experiments are reported to illustrate the robustness of the presented algorithm in Sect. 6.5. The chapter is concluded in Sect. 6.6.

As an emerging biometric technology, palmprint authentication has attracted considerable attention in recent years. In this field, coding-based methods, which extract the coding features of palmprint images, are among the most promising palmprint authentication methods. In this chapter, we first give a brief review of palmprint authentication methods in Sect. 4.1. Section 4.2 describes the conventional coding-based palmprint identification methods. In Sects. 4.3 and 4.4, two improved coding-based palmprint authentication methods are presented.

Malaysia has been recognized as one of the twelve nations endowed with rich biodiversity. Such huge number of species in the rain forest and sea are an important asset that need to be properly documented. Responding to these important needs, we have designed and evaluated a content based image retrieval system catered for marine life images. This paper investigates the effectiveness of various low level image descriptors, which includes the colour, shape and texture features in representing the semantic categories of the marine life images. This is a challenging task since the images are taken from different viewpoints and marine species do not possess consistent colour, shape and textural appearance. For the purpose of evaluating the overall image retrieval system effectiveness, we design and implement an image retrieval system which support image query by example. Experiment is conducted to evaluate the effectiveness of various low level image descriptors and the fusion of multiple features. The experiment result on the image retrieval performance is presented.

Progressive network based on detail scaling and texture extraction: A more general framework for image deraining

This paper presents a new vision based approach to vehicle re-identification (VRI) for smart transportation systems by fusion of multiple features. Unlike the conventional VRI systems which adopted loop sensors to capture inductive features for classification, we developed a hierarchical method for VRI by coarse-to-fine image matching. More specifically, VRI is performed at fine level by image matching using distinctive and anonymous features which are extracted from the large number of interesting points detected from the vehicle and its license plate images at coarse level. To achieve robustness, the thresholding of matching criteria is based on the dynamic analysis of the time series of vehicle images rather than predefined. In addition, the fusion of multiple features is conducted via a weighted probability scheme. To demonstrate the feasibility of the proposed new approach, a series of field testing were conducted, where 301 vehicles were considered for data calibration and 1699 vehicles were used for validation tests. The accuracy of matching rate reaches 73.51%. 85.52% and greater than 90% respectively by using density features, fusion of selected distinctive features and fusion of multimodal features.

Fusion of multiple features can boost the performance of large-scale visual classification and detection tasks like TRECVID Multimedia Event Detection (MED) competition [1]. In this paper, we propose a novel feature fusion approach, namely Feature Weighting via Optimal Thresholding (FWOT) to effectively fuse various features. FWOT learns the weights, thresholding and smoothing parameters in a joint framework to combine the decision values obtained from all the individual features and the early fusion. To the best of our knowledge, this is the first work to consider the weight and threshold factors of fusion problem simultaneously. Compared to state-of-the-art fusion algorithms, our approach achieves promising improvements on HMDB [8] action recognition dataset and CCV [5] video classification dataset. In addition, experiments on two TRECVID MED 2011 collections show that our approach outperforms the state-of-the-art fusion methods for complex event detection.