Papers by KRUPASHANKARI SANDYAL
International Journal for Research in Applied Science & Engineering Technology, 2020
Face recognition and its classification is a rapidly growing field in the area of image processin... more Face recognition and its classification is a rapidly growing field in the area of image processing and machine learning. Object recognition is a key feature of image classification and has its own numerous commercial implications. Facial gesture plays important role in many aspect, such as presence system, security and access system, and identification system. Model trained on diverse dataset to generalize better. Using deep region of interest (ROI) convolutional neural networks (CNNs) along with transfer learning are exploited. The Haar-Cascade is trained by superimposing the positive image over a set of negative images which is used to detect countenance.
License plate recognition has 3 main steps, the license plate detection, character segmentation a... more License plate recognition has 3 main steps, the license plate detection, character segmentation and recognition of character. After all the characters are read, it is important to accurately segment the characters. The segmentation step may be affected by many factors. Some of it might be frame or edges. For 100 percent accuracy the characters has to be segmented properly. Various image processing techniques are used for the segmentation process and using python code the characters are extracted. It should be useful to the law agencies but are not limited to that itself. LPR technology has a varied use. I.
Indonesian Journal of Electrical Engineering and Computer Science, Jul 1, 2023
India has more than 1,600 official languages, making it a multilingual country. Kannada, one of t... more India has more than 1,600 official languages, making it a multilingual country. Kannada, one of the major languages, originated in the state of Karnataka and is currently ranked 33 rd among the accents that are most often spoken throughout the world. However, the survey shows that much more effort is needed to create a complete handwritten identification system. Segmentation is one of the crucial steps in a handwriting identification system that extracts significant objects from an image. The feature extraction and classification phases of handwritten text recognition will be more successful if the segmentation approaches selected are efficient. In the proposed system, segmentation was accomplished using bounding box and contour tracing methods. The result got is delivered to the next step of handwritten identification system. An average accuracy of 92.6% is worked out for line segmentation and word segmentation.
Lecture notes on data engineering and communications technologies, Nov 11, 2019
Analysis of document images for information recovery has been exceptionally prominent in the late... more Analysis of document images for information recovery has been exceptionally prominent in the later past. Wide collection of information, which has been generally put away on paper, is as of now being changed over into electronic form for superior storage and intelligent processing. This needs processing of documents by utilizing different processing strategies. Preprocessing techniques are advantageous in the recognition of document images as well as medical images. The most significant goal of image recognition system is to perform operations on images to find patterns and to retrieve information from the images for feature extraction process. In this paper, we emphasize on various techniques for pre-processing an image that aids in the further process of Image recognition.
Analysis on Skew Detection and Rectification Techniques for Offline Handwritten Scripts
Indonesian Journal of Electrical Engineering and Computer Science
India has more than 1,600 official languages, making it a multilingual country. Kannada, one of t... more India has more than 1,600 official languages, making it a multilingual country. Kannada, one of the major languages, originated in the state of Karnataka and is currently ranked 33rd among the accents that are most often spoken throughout the world. However, the survey shows that much more effort is needed to create a complete handwritten identification system. Segmentation is one of the crucial steps in a handwriting identification system that extracts significant objects from an image. The feature extraction and classification phases of handwritten text recognition will be more successful if the segmentation approaches selected are efficient. In the proposed system, segmentation was accomplished using bounding box and contour tracing methods. The result got is delivered to the next step of handwritten identification system. An average accuracy of 92.6% is worked out for line segmentation and word segmentation.
Analysis on Skew Detection and Rectification Techniques for Offline Handwritten Scripts
Lecture notes in networks and systems, 2022
An Improved Handwritten Word Recognition Rate of South Indian Kannada Words Using Better Feature Extraction Approach
Advances in Intelligent Systems and Computing, 2015
Ever since the evolution of communication in human day to day activities, hand writing has gained... more Ever since the evolution of communication in human day to day activities, hand writing has gained its own impact and popularity. Therefore, Handwritten Word Recognition (HWR) is quite challenging due to heavy variations of writing style, different size and shape of the character by various writers. Accuracy and efficiency are the major parameters in the field of handwritten character recognition. However, with the progress in technology, human computer interactions have become a mandatory process to carry on the fast and dynamic demanding activities of the everyday cycle. This paper thus throws light on an effective recognition process for the handwritten word recognition. The HWR is carried out in 3 stages. In the first stage, pre-processing removes the unwanted data like noise and the second stage extracts the best features such as the sharp corners, curves and loops and finally the third stage of the process classifies the image under the correct matching class using the Euclidean distance based classifier. This process is implemented and the results indicate an improved accuracy and efficient recognition rate.
A Survey on Offline Recognition of South Indian Scripts
Handwritten character recognition is always a frontier area of research in the field of pattern r... more Handwritten character recognition is always a frontier area of research in the field of pattern recognition. Even though, sufficient studies have performed in foreign scripts like Arabic, Chinese and Japanese, only a very few work can be traced for handwritten character recognition mainly for the south Indian scripts. Multiple combinations of vowels and consonants along with its modifiers led to generation of huge number of classes with respect to character recognition systems. The feature extraction and classification of characters from such huge number of classes in south Indian language Optical Character Recognitions remains as a non-trivial problem.OCR system development for Indian script has many application areas like preserving manuscripts and ancient literatures written in different Indian scripts and making digital libraries for the documents. Feature extraction and classification are essential steps of character recognition process affecting the overall accuracy of the rec...
Intelligent Data Communication Technologies and Internet of Things, 2019
Analysis of document images for information recovery has been exceptionally prominent in the late... more Analysis of document images for information recovery has been exceptionally prominent in the later past. Wide collection of information, which has been generally put away on paper, is as of now being changed over into electronic form for superior storage and intelligent processing. This needs processing of documents by utilizing different processing strategies. Pre-processing techniques are advantageous in the recognition of document images as well as medical images. The most significant goal of image recognition system is to perform operations on images to find patterns and to retrieve information from the images for feature extraction process. In this paper, we emphasize on various techniques for pre-processing an image that aids in the further process of Image recognition.
Offline Handwritten Text Recognition (HTR) is one of the most interesting challenges in today'... more Offline Handwritten Text Recognition (HTR) is one of the most interesting challenges in today's date in the field of Image processing. This paper introduces a novel technique to recognize the handwritten text by using Convolutional Recurrent Neural Network along with Connectionist Temporal Classification. This model makes use of the IAM dataset. Offline Signature Verification (SV) is another challenging task in the field of biometrics. This paper demonstrates a novel technique to verify the signature as an original or forged one, and makes use of the Convolutional Siamese network.
Uploads
Papers by KRUPASHANKARI SANDYAL