Human–computer interaction (HCI) and related technologies focus on the implementation of interactive computational systems. The studies in HCI emphasize on system use, creation of new techniques that support user activities, access to information, and ensures seamless communication. The use of artificial intelligence and deep learning-based models has been extensive across various domains yielding state-of-the-art results. In the present study, a crow search-based convolution neural networks model has been implemented in gesture recognition pertaining to the HCI domain. The hand gesture dataset used in the study is a publicly available one, downloaded from Kaggle. In this work, a one-hot encoding technique is used to convert the categorical data values to binary form. This is followed by the implementation of a crow search algorithm (CSA) for selecting optimal hyper-parameters for training of dataset using the convolution neural networks. The irrelevant parameters are eliminated from consideration, which contributes towards enhancement of accuracy in classifying the hand gestures. The model generates 100 percent training and testing accuracy that justifies the superiority of the model against traditional state-of-the-art models.

/pdf/hand-gesture-classification-using-a-novel-cnn-crow-search-5ecktcwta5.pdf

Hand gesture classification using a novel CNN-crow search algorithm

Distinguishing between natural images (NIs) and computer-generated (CG) images by naked human eyes is difficult. In this paper, we propose an effective method based on a convolutional neural network (CNN) for this fundamental image forensic problem. Having observed the rather limited performance of training existing CCNs from scratch or fine-tuning pre-trained network, we design and implement a new and appropriate network with two cascaded convolutional layers at the bottom of a CNN. Our network can be easily adjusted to accommodate different sizes of input image patches while maintaining a fixed depth, a stable structure of CNN, and a good forensic performance. Considering the complexity of training CNNs and the specific requirement of image forensics, we introduce the so-called local-to-global strategy in our proposed network. Our CNN derives a forensic decision on local patches, and a global decision on a full-sized image can be easily obtained via simple majority voting. This strategy can also be used to improve the performance of existing methods that are based on hand-crafted features. Experimental results show that our method outperforms existing methods, especially in a challenging forensic scenario with NIs and CG images of heterogeneous origins. Our method also has good robustness against typical post-processing operations, such as resizing and JPEG compression. Unlike previous attempts to use CNNs for image forensics, we try to understand what our CNN has learned about the differences between NIs and CG images with the aid of adequate and advanced visualization tools.

Distinguishing Between Natural and Computer-Generated Images Using Convolutional Neural Networks

In this paper, a novel forensics scheme for color image is proposed in color quaternion wavelet transform (CQWT) domain. Compared with discrete wavelet transform (DWT), contourlet wavelet transform, and local binary patterns, CQWT processes a color image as a unit, and so, it can provide more forensics information to identify the photograph (PG) and computer generated (CG) images by considering the quaternion magnitude and phase measures. Meanwhile, two novel quaternion central moments for color images, i.e., quaternion skewness and kurtosis, are proposed to extract forensics features. In the condition of the same statistical model as Farid’s model, the CQWT can boost the performance of the existing identification models. Compared with Farid’s model and Li’s model in 7500 PG and 7500 CG, the quaternion statistical features show a better classification performance. Results in the comparative experiments show that the classification accuracy of the CQWT improves by 19% more than Farid’s model, and the quaternion features approximately improve by 2% more than the traditional.

Identifying Computer Generated Images Based on Quaternion Central Moments in Color Quaternion Wavelet Domain

Tradition reference table based (RTB) methods employ two pixels to conceal a secret digit according to a two-dimensional reference table. In this paper, x-dimensional reference table framework is defined, which can be regarded as generalization of the prior works. The available pixels to be embedded are limited in two-dimensional space, so the proposed methods extend the dimensional space of reference table. Theoretical analyses are given to justify the effectiveness of the proposed construction. Two novel RTB methods named CRT (cubic reference table) and CRT-PVD (cubic reference table and pixel value differencing) are presented. The former is independent of image contents while embedding, and the latter is depended on the discriminated image smoothness. Experimental results show that two proposed methods can achieve better performance compared with the prior works.

New cubic reference table based image steganography

Aiming to counter presentation attack (also known as spoofing attack) in face recognition system, a face presentation attack detection (also known as spoofing detection or liveness detection) scheme based on guided scale texture is proposed. In order to minimize the influence of the redundant noise contamination, guided scale space is proposed to reduce the redundancy of the original facial texture and to extract more powerful facial edges. Based on the guided scale space, two guided scale texture descriptors are proposed to extract liveness detection features, and they are guided scale based local binary pattern (GS-LBP) and local guided binary pattern (LGBP). GS-LBP takes advantage of the edge-preserving property of the guided scale space, and joint quantization is used in LGBP to encode the neighboring relationships of the original face and the guided scale face without using additional features. With the guided scale texture features, presentation attack detection is accomplished by the use of a linear support vector machine classifier. Experiments are done with public MSU MFSD, CASIA FASD, Replay-Attack and Replay-Mobile databases, and the results indicate its effectiveness. The proposed method can effectively be applied for countering photo attack and video attack in face recognition systems.

Face presentation attack detection using guided scale texture

The aim of the work presented in this paper is to discriminate natural images (NI) and computer generated graphics (CG). The texture differences are analyzed to the residual images of NI and CG. The residual images are first extracted by using multiple linear regressions, and then the fitting degree of the regression model is investigated. Through the analysis of the difference of their residual images, 9 dimensions of histogram features and 9 dimensions of multi-fractal spectrum features are extracted to represent their texture differences. Combined with 6 dimensions of regression model fitness features, natural images and computer generated graphics are discriminated by using a support vector machine (SVM) classifier. Experimental results and analysis show that it can achieve an average identification accuracy of 98.69%, and it is robust against JPEG compression, rotation, additive noise and image resizing. Compared with some existed methods, the selection of features is effective and fewer features are required for representing the differences between NI and CG. Meanwhile, the classification time is significantly reduced and the robustness is maintained. It has great potential to be used in image source pipeline identification.

Die-lan Zhou

Papers

Discrimination of natural images and computer generated graphics based on multi-fractal and regression analysis

Discriminating natural images and computer generated graphics based on the impact of CFA interpolation on the correlation of PRNU