Sensor pattern noise (SPN) extraction is a critical stage of the sensor based source camera identification (SCI). However, the quality of the extracted SPN with the traditional discrete wavelet transform (DWT) based method is poor around strong edges and along with the image border. To fill this gap, we propose a dual tree complex wavelet transform (DTCWT) based method to extract the SPN from a given image, which achieves better performance in the area around strong edges. Furthermore, symmetric boundary extension instead of the periodized boundary extension is used for enhancing the quality of SPN along with the image border. Extensive experimental results on both synthetic noisy images and real-world photographs clearly demonstrate the superior SCI performance of the proposed method over state-of-the-arts. Moreover, the proposed method also shows potential in the application of image tampering localization.

Deep learning models often have complicated structures with low computational speed and the requirement of a large amount of storage space, which limits their own practical application on some devices with insufficient computing power. This paper proposes the weight and structure determination neural network aided with double pseudoinversion (WASDNN-DP) that can overcome these shortcomings. First, the model structure, theoretical bases, and the algorithms of WASDNN-DP are given. In the process of constructing the network, the weight matrix between the hidden layer and the output layer is first randomly generated. After the weight matrix between the input layer and the hidden layer is analytically determined, the weight matrix between the hidden layer and the output layer is re-determined by the pseudo-inverse method. Furthermore, in WASDNN-DP, the structure of the neural network is determined by a progressive method. Subsequently, based on two datasets collected from children aged 7-15 years by using smart insoles, the comparative experiments between WASDNN-DP and some other machine learning models are carried out, which illustrate the superiority of the proposed WASDNN-DP in the diagnosis of flat foot.

This work addresses the median filtering forensics for lossy compressed image with low resolution, which is essential for identification of fake images and fake videos. A deep residual model with training data augmentation is employed in the proposed method. To solve the dilemma that the low-resolution image is lack of enough statistical pixels for extracting reliable features, we propose a filter layer to widen the inputs for the convolutional neural network (CNN). First, we perform high-pass filtering to an image in the filtered layer, and stack the multiple filtered residuals into 16-channel feature maps as inputs of CNN. Then, a deep residual CNN model is proposed to self-learn the median filtering traces that are hidden in the JPEG lossy compressed image. To alleviate the over-fitting issue of the deeper CNN model, we employ a data augmentation scheme in the training to increase the diversity of training data and thus obtain a more stable median filtering detector. Experimental results demonstrate that the proposed net with training data augmentation outperforms state-of-the-arts in both baseline test and generalization ability test, achieving at least 2% higher in term of detection accuracy.