Vehicle make and model recognition (VMMR) is a key task for automated vehicular surveillance (AVS) and various intelligent transport system (ITS) applications. In this paper, we propose and study the suitability of the bag of expressions (BoE) approach for VMMR-based applications. The method includes neighborhood information in addition to visual words. BoE improves the existing power of a bag of words (BOW) approach, including occlusion handling, scale invariance and view independence. The proposed approach extracts features using a combination of different keypoint detectors and a Histogram of Oriented Gradients (HOG) descriptor. An optimized dictionary of expressions is formed using visual words acquired through k-means clustering. The histogram of expressions is created by computing the occurrences of each expression in the image. For classification, multiclass linear support vector machines (SVM) are trained over the BoE-based features representation. The approach has been evaluated by applying cross-validation tests on the publicly available National Taiwan Ocean University-Make and Model Recognition (NTOU-MMR) dataset, and experimental results show that it outperforms recent approaches for VMMR. With multiclass linear SVM classification, promising average accuracy and processing speed are obtained using a combination of keypoint detectors with HOG-based BoE description, making it applicable to real-time VMMR systems.

In this paper, the Deep Neural Network (DNN) based classification of five fingers Electromyography (EMG) pattern is presented. The aim is to improve EMG signal acquisition and classification accuracy for the robustness of hand control prosthetics. Wavelet Transform (WT) is used to extract a total of 500 feature vectors from five fingers that are used to train an autoencoder based five-layered Deep Neural Network (DNN). The hidden layer holds Sparse Autoencoders followed by a SoftMax layer that are stacked together to form multi-layered feed forward network. Finally, the conjugate gradient backpropagation technique is performed on the whole DNN for mitigating the Mean Square Error (MSE) used to define the performance of DNN. The MSE is evaluated for 5 and 10 neurons being used in the hidden layer which get stabilized at about 500 epochs to a very low value of 0.010498. The overall results showed that designed system is able to capture optimum EMG signals having meaningful information and promises a fruitful accuracy rate of 99.3% with an average error rate of 0.7% for the given dataset. The superlative performance of DNN has shown edge over the existing techniques in literature due to its robustness. In future similar techniques can be extended for use in classification of simultaneous movement of fingers which in turn could provide genuine movements for amputees as compared to exclusive classification of distinct movements.

Human action recognition has gathered significant attention in recent years due to its high demand in various application domains. In this work, we propose a novel codebook generation and hybrid encoding scheme for classification of action videos. The proposed scheme develops a discriminative codebook and a hybrid feature vector by encoding the features extracted from CNNs (convolutional neural networks). We explore different CNN architectures for extracting spatio-temporal features. We employ an agglomerative clustering approach for codebook generation, which intends to combine the advantages of global and class-specific codebooks. We propose a Residual Vector of Locally Aggregated Descriptors (R-VLAD) and fuse it with locality-based coding to form a hybrid feature vector. It provides a compact representation along with high order statistics. We evaluated our work on two publicly available standard benchmark datasets HMDB-51 and UCF-101. The proposed method achieves 72.6% and 96.2% on HMDB51 and UCF101, respectively. We conclude that the proposed scheme is able to boost recognition accuracy for human action recognition.