Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

Head pose estimation (HPE) has wide industrial applications, such as online education, human–robot interaction, and automatic manufacturing. In this article, we address two key problems in HPE based on label learning and asymmetric relation cues: 1) how to bridge the gap between the better prediction performance of networks and incorrectly label pose images in the HPE datasets and 2) how to take full advantage of the adjacent poses information around the centered pose image. We reconstruct all the incorrect labels as a two-dimensional Lorentz distribution to tackle the first problem. Instead of directly adopting the angle values as hard labels, we assign part of the probability values (soft labels) to adjacent labels for learning discriminative feature representations. To address the second problem, we reveal the asymmetric relation nature of HPE datasets. The yaw direction and pitch direction are assigned different weights by introducing the half at half-maximum of the Lorentz distribution. Compared with the traditional end-to-end frameworks, the proposed one can leverage the asymmetric relation cues for predicting the head pose angle in the incorrect label scenarios. Extensive experiments on two public datasets and our infrared dataset demonstrate that the proposed ARHPE network significantly outperforms other state-of-the-art approaches.

ARHPE: Asymmetric Relation-Aware Representation Learning for Head Pose Estimation in Industrial Human–Computer Interaction

In this paper, we present Discriminant Correlation Analysis (DCA), a feature level fusion technique that incorporates the class associations in correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pair-wise correlations across the two feature sets, and at the same time, eliminating the between-class correlations and restricting the correlations to be within classes. Our proposed method can be used in pattern recognition applications for fusing features extracted from multiple modalities or combining different feature vectors extracted from a single modality. It is noteworthy that DCA is the first technique that considers class structure in feature fusion. Moreover, it has a very low computational complexity and it can be employed in realtime applications. Multiple sets of experiments performed on various biometric databases show the effectiveness of our proposed method, which outperforms other state-of-the-art approaches.

Discriminant correlation analysis for feature level fusion with application to multimodal biometrics

Object detection is one of the most fundamental and challenging tasks to locate objects in images and videos. Over the past, it has gained much attention to do more research on computer vision tasks such as object classification, counting of objects, and object monitoring. This study provides a detailed literature review focusing on object detection and discusses the object detection techniques. A systematic review has been followed to summarize the current research work’s findings and discuss seven research questions related to object detection. Our contribution to the current research work is (i) analysis of traditional, two-stage, one-stage object detection techniques, (ii) Dataset preparation and available standard dataset, (iii) Annotation tools, and (iv) performance evaluation metrics. In addition, a comparative analysis has been performed and analyzed that the proposed techniques are different in their architecture, optimization function, and training strategies. With the remarkable success of deep neural networks in object detection, the performance of the detectors has improved. Various research challenges and future directions for object detection also has been discussed in this research paper. 

/pdf/tools-techniques-datasets-and-application-areas-for-object-3vlq1i2m.pdf

Tools, techniques, datasets and application areas for object detection in an image: a review

A novel facial expression recognition system has been proposed in this paper. The objective of this paper is to recognize the types of expressions in the human face region. The implementation of the proposed system has been divided into four components. In the first component, a region of interest as face detection has been performed from the captured input image. For extracting more distinctive and discriminant features, in the second component, a deep learning-based convolutional neural network architecture has been proposed to perform feature learning tasks for classification purposes to recognize the types of expressions. To enhance the performance of the proposed system, in the third component, some novel data augmentation techniques have been applied to the facial image to enrich the learning parameters of the proposed CNN model. In the fourth component, a trade-off between data augmentation and deep learning features have been performed for fine-tuning the trained CNN model. Extensive experimental results have been demonstrated using three benchmark databases: KDEF (seven expression classes), GENKI-4k (two expression classes), and CK+ (seven expression classes). The performance of the proposed system respect for each database has been well presented and described and finally, these performances have been compared with the existing state-of-the-art methods. The comparison with competing methods shows the superiority of the proposed system.

Facial expression recognition with trade-offs between data augmentation and deep learning features

A novel cancelable FaceHashing technique based on non-invertible transformation with encryption and decryption template has been proposed in this paper. The proposed system has four components: face preprocessing, feature extraction, cancelable feature extraction followed by the classification, and encryption/decryption of cancelable face feature templates. During face preprocessing, the facial region of interest has been extracted out to speed the process for evaluating discriminant features. In feature extraction, some optimization techniques such as Sparse Representation Coding, Coordinate descent, and Block coordinates descent have been employed on facial descriptors to obtain the best representative of those descriptors. The representative descriptors are further arranged in a spatial pyramid matching structure to extract more discriminant and distinctive feature vectors. To preserve them, the existing BioHashing technique has been modified and extended to some higher levels of security attacks and the modified BioHashing technique computes a cancelable feature vector by the combined effect of the facial feature vector and the assigned token correspond to each user. The elements of computed cancelable feature vector are in a numeric form that has been employed to perform both verifications as well as identification task in online while the original facial feature vectors are kept offline either in hard drive or disc. Then, to enhance more security levels and also to preserve the cancelable face features, an RSA based encryption-decryption algorithm has been introduced. The proposed system has been tested using four benchmark face databases: CASIA-FACE-v5, IITK, CVL, and FERET, and performance are obtained as correct recognition rate and equal error rate. The performance are compared to the state-of-the-art methods for the superiority of the proposed feature extraction technique and individual performance analysis has been performed at all the security levels of the proposed Cancelable FaceHashing Technique. These comparisons show the superiority of the proposed system.

/pdf/a-novel-cancelable-facehashing-technique-based-on-non-3pbstbxn0e.pdf

Chiara Pero

Papers

Facial expression recognition with trade-offs between data augmentation and deep learning features

A Novel Cancelable FaceHashing Technique Based on Non-invertible Transformation with Encryption and Decryption Template

Head pose estimation by regression algorithm

Adversarial attacks through architectures and spectra in face recognition

User recognition based on periocular biometrics and touch dynamics