Lung nodules are vital indicators for the presence of lung cancer. An early detection enhances the survival rate of the patient by starting treatment at the right time. The detection and classification of malignancy in Computed Tomography (CT) images is a very time-consuming and difficult task for radiologists which lead the researchers to develop algorithms for Computer-Aided Diagnosis (CAD) systems to mitigate this burden. The performance of CAD systems is continuously improving by using various deep learning techniques for screening of lung cancer. In this paper, we proposed transferable texture Convolutional Neural Networks (CNN) to improve the classification performance of pulmonary nodules in CT scans. An Energy Layer (EL) is incorporated in our scheme, which extracts texture features from the convolutional layer. The inclusion of EL reduces the number of learnable parameters of the network, which further reduces the memory requirements and computational complexity. The proposed model has only three convolutional layers and one EL, instead of pooling layer. Overall proposed CNN architecture comprises of nine layers for automatic feature extraction and classification of pulmonary nodule candidates as malignant or benign. Furthermore, the pre-trained model of proposed CNN is also used to handle the smaller dataset classification problem by using transfer learning. This work has been evaluated on publicly available LIDC-IDRI and the LUNGx Challenge database through different evaluation matrices, such as; the accuracy, specificity, error rate and AUC. The proposed model is trained by six-fold cross-validation and achieved an accuracy score of 96.69%±0.72% with only 3.30%±0.72% error rate. Whereas, the measured AUC and recall is 99.11%±0.45% and 97.19%±0.57%, respectively. Moreover, we also tested our proposed technique on the MNIST dataset and achieved state-of-the-art results in terms of accuracy and error rate.

The existence of pulmonary nodules exhibits the presence of lung cancer. The Computer-Aided Diagnostic (CAD) and classification of such nodules in CT images lead to improve the lung cancer screening. The classic CAD systems utilize nodule detector and feature-based classifier. In this work, we proposed a decision level fusion technique to improve the performance of the CAD system for lung nodule classification. First, we evaluated the performance of Support Vector Machine (SVM) and AdaBoostM2 algorithms based on the deep features from the state-of-the-art transferable architectures (such as; VGG-16, VGG-19, GoogLeNet, Inception-V3, ResNet-18, ResNet-50, ResNet-101 and InceptionResNet-V2). Then, we analyzed the performance of SVM and AdaBoostM2 classifier as a function of deep features. We also extracted the deep features by identifying the optimal layers which improved the performance of the classifiers. The classification accuracy is increased from 76.88% to 86.28% for ResNet-101 and 67.37% to 83.40% for GoogLeNet. Similarly, the error rate is also reduced significantly. Moreover, the results showed that SVM is more robust and efficient for deep features as compared to AdaBoostM2. The results are based on 4-fold cross-validation and are presented for publicly available LUNGx challenge dataset. We showed that the proposed technique outperforms as compared to state-of-the-art techniques and achieved accuracy score was 90.46 ± 0.25%.

The Pulmonary nodule indicates the presence of lung cancer. The deep convolutional neural networks (DCNNs) have been widely used to classify the pulmonary nodule as benign or malignant. However, an individual learner usually performs unsatisfactorily due to limited response space, incorrect selection of hypothesis space, or falling into local minimums. To investigate these issues, we propose ensemble learners fusion techniques based on averaging of prediction score and maximum vote score (MAX-VOTE). First, the support vector machine (SVM) and AdaBoostM2 machine learning algorithms are trained on the deep features from DCNNs. The results of both classifiers are fused separately based on averaging of the prediction score. Secondly, the feature fusion technique is developed by fusing the feature of three DCNNs (AlexNet, VGG-16 and VGG-19) through predefined rules. After that, the SVM and AdaBoostM2 are trained on fused features independently to build ensemble learners by fusing the multiple DCNN learners. The predictions of all DCNN learners are fused based on the MAX-VOTE. The results show that the ensemble learners based MAX-VOTE technique yields better performance out of twelve single learners for binary class classification of pulmonary nodules. The proposed fusion techniques are also tested for multi-class classification problem. The SVM based feature fusion technique performs better as compared to all the implemented and the state-of-the-art techniques. The achieved maximum accuracy, AUC and specificity scores are 96.89%±0.25, 99.21%±0.10 and 97.70%±0.21, respectively.

Multi-focus image fusion is a very essential method of obtaining an all focus image from multiple source images. The fused image eliminates the out of focus regions, and the resultant image contains sharp and focused regions. A novel multiscale image fusion system based on contrast enhancement, spatial gradient information and multiscale image matting is proposed to extract the focused region information from multiple source images. In the proposed image fusion approach, the multi-focus source images are firstly refined over an image enhancement algorithm so that the intensity distribution is enhanced for superior visualization. The edge detection method based on a spatial gradient is employed for obtaining the edge information from the contrast stretched images. This improved edge information is further utilized by a multiscale window technique to produce local and global activity maps. Furthermore, a trimap and decision maps are obtained based upon the information provided by these near and far focus activity maps. Finally, the fused image is achieved by using an enhanced decision maps and fusion rule. The proposed multiscale image matting (MSIM) makes full use of the spatial consistency and the correlation among source images and, therefore, obtains superior performance at object boundaries compared to region-based methods. The achievement of the proposed method is compared with some of the latest techniques by performing qualitative and quantitative evaluation.

Correct recognition of vehicles violating traffic rules and regulations is a major challenge in the present complex traffic environment. Automatic Number Plate Recognition (ANPR) systems plays an important role in the detection of such events. ANPR systems are typically standalone systems using the capabilities of embedded processors for correct recognition. The limited processing capabilities hinders the efficient determination of location of number plates in such images satisfying the real time criteria. This paper presents an adopted method for the image preprocessing, image detection and extraction of standardized white background vehicle number plates. Application of suitable Gaussian Filters along with other image preprocessing techniques, Binary jumps and Image differencing techniques have been carried out in this work. An ARM Cortex A8 processor with 1GHz processor and 512 MB RAM has been selected as the candidate embedded processor in this work. Experiments show that the proposed method posses over 90% accuracy.

This paper proposes a fast Adaptive Modified Hexagon Based Search (AMHexBS) Motion Estimation (ME) algorithm. The proposed algorithm predicts the direction of motion by using rood shaped pattern and then Hexagonal based Search (HexBS) is applied for refinement of search process. The size of rood shaped pattern is dynamically determined for each Macro Block (MB). An early termination scheme is incorporated to speed-up the ME process, which is mainly advantageous for the video sequences having low motion activities. The simulation results show that the proposed algorithm performs better according to Speed Improvement Rate (SIR) and number of search points for low and moderate motion video sequences.