Traditional systems of handwriting recognition have relied on handcrafted features and a large amount of prior knowledge. Training an Optical character recognition (OCR) system based on these prerequisites is a challenging task. Research in the handwriting recognition field is focused around deep learning techniques and has achieved breakthrough performance in the last few years. Still, the rapid growth in the amount of handwritten data and the availability of massive processing power demands improvement in recognition accuracy and deserves further investigation. Convolutional neural networks (CNNs) are very effective in perceiving the structure of handwritten characters/words in ways that help in automatic extraction of distinct features and make CNN the most suitable approach for solving handwriting recognition problems. Our aim in the proposed work is to explore the various design options like number of layers, stride size, receptive field, kernel size, padding and dilution for CNN-based handwritten digit recognition. In addition, we aim to evaluate various SGD optimization algorithms in improving the performance of handwritten digit recognition. A network’s recognition accuracy increases by incorporating ensemble architecture. Here, our objective is to achieve comparable accuracy by using a pure CNN architecture without ensemble architecture, as ensemble architectures introduce increased computational cost and high testing complexity. Thus, a CNN architecture is proposed in order to achieve accuracy even better than that of ensemble architectures, along with reduced operational complexity and cost. Moreover, we also present an appropriate combination of learning parameters in designing a CNN that leads us to reach a new absolute record in classifying MNIST handwritten digits. We carried out extensive experiments and achieved a recognition accuracy of 99.87% for a MNIST dataset.

This study addresses the problem of the automatic detection of disease states of the retina. In order to solve the abovementioned problem, this study develops an artificially intelligent model. The model is based on a customized 19-layer deep convolutional neural network called VGG-19 architecture. The model (VGG-19 architecture) is empowered by transfer learning. The model is designed so that it can learn from a large set of images taken with optical coherence tomography (OCT) and classify them into four conditions of the retina: (1) choroidal neovascularization, (2) drusen, (3) diabetic macular edema, and (4) normal form. The training datasets (taken from publicly available sources) consist of 84,568 instances of OCT retinal images. The datasets exhibit all four classes of retinal disease mentioned above. The proposed model achieved a 99.17% classification accuracy with 0.995 specificities and 0.99 sensitivity, making it better than the existing models. In addition, the proper statistical evaluation is done on the predictions using such performance measures as (1) area under the receiver operating characteristic curve, (2) Cohen’s kappa parameter, and (3) confusion matrix. Experimental results show that the proposed VGG-19 architecture coupled with transfer learning is an effective technique for automatically detecting the disease state of a retina.

Character Segmentation is the most crucial step for any OCR (Optical Character Recognition) System. The selection of segmentation algorithm being used is the key factor in deciding the accuracy of OCR system. If there is a good segmentation of characters, the recognition accuracy will also be high. Segmentation of words into characters becomes very difficult due to the cursive and unconstrained nature of the handwritten script. This paper proposes a new vertical segmentation algorithm in which the segmentation points are located after thinning the word image to get the stroke width of a single pixel. The knowledge of shape and geometry of English characters is used in the segmentation process to detect ligatures. The proposed segmentation approach is tested on a local benchmark database and high segmentation accuracy is found to be achieved.

Background: The data proliferation has been resulted in large-scale, high dimensional data and brings new challenges for feature selection in handwriting recognition problems. The practical challenges like the large variability and ambiguities present in the individual’s handwriting style demand an optimal feature selection algorithm that would be capable to enhance the recognition accuracy of handwriting recognition system with reduced training efforts and computational cost. Objective: This paper gives emphasis on the feature selection process and proposed a genetic algorithm based feature selection technique for handwritten digit recognition. Methods: A hybrid feature set of statistical and geometrical features is developed in order to get the effective feature set consist of local and global characteristics of sample digits. The method utilizes a genetic algorithm based feature selection for selecting best distinguishable features and k-nearest neighbour for evaluating the fitness of features of handwritten digit dataset. Results: The experiments are carried out on standard The Chars74K handwritten digit dataset and reported a 66% reduction in the original feature set without sacrificing the recognition accuracy. Conclusion: The experiment results show the effectiveness of the proposed approach.