<p>From their initial days, the fields of computer vision and image processing have been dealing with visual recognition problems. Convolutional Neural Networks (CNNs) in machine learning are deep architectures built as feed-forward neural networks or perceptrons, which are inspired by the research done in fields of visual analysis by the visual cortex of mammals like cats. This work analyzes CNNs for computer vision tasks, natural language processing, fundamental sciences and engineering problems, and other miscellaneous tasks. The general CNN structure, along with its mathematical intuition and working, a brief critical commentary on the advantages and disadvantages, which leads researchers to search for alternatives to CNN, is also mentioned. The paper also serves as an appreciation of the brain-child of past researchers for the existence of such a prolific architecture for handling multidimensional data and approaches to improve their performance further. </p>
<p>From their initial days, the fields of computer vision and image processing have been dealing with visual recognition problems. Convolutional Neural Networks (CNNs) in machine learning are deep architectures built as feed-forward neural networks or perceptrons, which are inspired by the research done in fields of visual analysis by the visual cortex of mammals like cats. This work analyzes CNNs for computer vision tasks, natural language processing, fundamental sciences and engineering problems, and other miscellaneous tasks. The general CNN structure, along with its mathematical intuition and working, a brief critical commentary on the advantages and disadvantages, which leads researchers to search for alternatives to CNN, is also mentioned. The paper also serves as an appreciation of the brain-child of past researchers for the existence of such a prolific architecture for handling multidimensional data and approaches to improve their performance further. </p>
This paper presents a novel geometrical scale and rotation independent feature extraction (FE) technique for multilingual character recognition (CR). The performance of any CR techniques mainly depends on the robustness of the proposed FE methods. Currently, there are very few scale and rotation independent FE techniques present in the literature which successfully extract the robust features from characters with noise such as distortion and breaks in the characters. Many FE methods from the literature failed to distinguish the characters which look similar in their appearance. So, in this paper, we have proposed a novel scale and rotation independent geometrical shape FE technique which successfully recognized distorted, broken, and similarly looking characters. Aside from the proposed FE technique, we've used crossing count (CC) features. Finally, we have combined the proposed features with CC features to make as Feature Vector (FV) of the character to be recognized. The proposed CR technique is evaluated using publicly available media-lab license plate (LP), ISI_Bengali, and Chars74K benchmark data sets and achieved encouraging results. To further assess the performance of the proposed FE method, we've used a proprietary data set containing nearly 168000 multilingual characters from English, Devanagari, and Marathi scripts and achieved encouraging results. We have observed better classification rates for the proposed FE method using publicly available benchmark data sets as compared to few of the CR FE methods from the literature.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.