Search

In the modern era, the necessity of digitization is increasing in a rapid manner day-to-day. The healthcare industries are working towards operating in a paperless environment. Digitizing the medical lab records help the patients in hassle-free management of their medical data. It may also prove beneficial for insurance companies for designing various medical insurance policies which can be patient-centric rather than being generalized. Optical Character Recognition (OCR) technology is demonstrated its usefulness for such cases and thus, to know the best possible solution for digitizing the medical lab records, there is a need to perform an extensive comparative study on the different OCR techniques available for this purpose. It is observed that the current research is focused mainly on the pre-processing image techniques for OCR development, however, their effects on OCR performance specially for medical report digitization yet not been studied. Herein this work, three OCR Engines viz Tesseract, EasyOCR and DocTR, and 6 pre-processing techniques: image binarization, brightness transformations, gamma correction, sigmoid stretching, bilateral filtering and image sharpening are surveyed in detail. In addition, an extensive comparative study of the performance of the OCR Engines while applying the different combinations of the image pre-processing techniques, and their effect on the OCR accuracy is presented.

As a precursor of optical character recognition (OCR) technology, script identification finds many applications like sorting and indexing of document images. Classifying these scripts, especially at different scales and orientations, is one of the interesting and vital problems in the field of document image analysis. In this paper, an algorithm is proposed for the identification of scripts using scale and rotation robust log-polar wavelet and semi decimated wavelet features. Initially, words are segmented from document images in the form of text-blobs by the Gaussian filter. Then, texture features are calculated using a combination of discrete wavelet and semi decimated discrete wavelet transforms in log-polar domain. Here, most of the rotational and scale variations are removed in log-polar domain, whereas wavelet transform is capable of extracting the information at different resolution levels. This helps in the formation of significant textures for the purpose of characterization. At last, k-nearest neighbor classifier is used for the identification of scripts. Comprehensive experiments on different databases illustrate the effectiveness of the proposed algorithm. Benchmarking analysis shows that a maximum recall rate of 98.96% is obtained, and demonstrates better performance compared to the other contemporary approaches.

‘Internet of things’ (IoT) realize a network of millions of connected devices like sensors, actuators and transceivers. Being a composite system, IoT must deal with the associated problems while meeting throughput, latency, energy consumption, and security criteria. In this work, wireless technologies have been classified based on the mechanisms of physical layer, media access control layer, and network layer. The fundamentals of wireless communication and all the non-trivial interests associated with these three layers are summarized with respect to the criteria imposed by IoT. Various security threats at these layers and vulnerabilities of the standards against such attacks have also been listed out. To mitigate these problems, instead of relying on any one particular solution, more emphasis is given on the integrated approach where layer-wise solutions are provided. Thereafter, a brief analysis of the available wireless communication standards and their salient features are discussed. Research scope and challenges in IoT applications ranging from low power, low data rate, short range to extended coverage are identified, followed by possible directions to be taken. Additionally, the third generation partnership project for low-power wide area solutions to meet the IoT requirements are analyzed in detail.

Nowadays, in document analysis, optical character recognition (OCR) finds application in the exhaustive searching processes within memory hard drives and web. In OCR-related applications, s...

To make paperless environment in office, document image analysis, where optical character recognition is mostly used, plays a major role. The documents such as bank cheques, admission forms, application forms, memorandums and letters generally consist of text material in mixed form, i.e., handwritten and machine-printed texts along with some noises. Because of this mixture, significant issues raise in the recognition process. By separating out handwritten and machine-printed texts, a solution is offered to overcome this problem. In this paper, a new algorithm is proposed for separation of machine-printed and handwritten texts using correlation coefficients and probabilities-based moments features. Contourlet transform is used to extract these significant features because it has excellent directional and isotropic properties. Finally, set of support vector machines classifiers is used to identify machine-printed text, handwritten text and noise. Comprehensive experiments on different databases show that the proposed algorithm is robust and it provides a better text separation performance compared to that of other state-of-the-art approaches. In benchmarking analysis, maximum identification recall rate of 98.9% is obtained from the proposed technique, which demonstrates its effectiveness.

This paper presents robust methods for character segmentation and recognition for multilingual (Latin and Devanagari) Indian document images. The documents degraded over the years because of text d...

In this paper, robust algorithms for character segmentation and recognition are presented for multilingual Indian document images of Latin and Devanagari scripts. These documents generally suffer from their layout organizations, local skews, and low print quality and contain intermixed texts (machine-printed and handwritten). In the proposed character segmentation algorithm, primary segmentation paths are obtained using structural property of characters, whereas overlapped and joined characters are separated using graph distance theory. Finally, segmentation results are validated using highly accurate support vector machine classifier. For the proposed character recognition algorithm, three new geometrical shape-based features are computed. First and second features are formed with respect to the center pixel of character, whereas neighborhood information of text pixels is used for the calculation of third feature. For recognizing the input character, $k$ -Nearest Neighbor classifier is used, as it has intrinsically zero training time. Comprehensive experiments are carried out on different databases containing printed as well as handwritten texts. Benchmarking results illustrate that proposed algorithms have better performances compared to other contemporary approaches, where highest segmentation and recognition rates of 98.86% and 99.84%, respectively, are obtained.

One of the major applications of text retrieval from images is to extract the text information and then recognize its characters. This is helpful for indexing the images within storage media. When we want to search a particular image or document, there is no need to go through a large bunch of images. We go only through the group of indexed images, so that the task of finding the particular image becomes easy. Extracting text lines from scanned document images present a major problem in optical character recognition process as skewed text lines raise the complexity. The problem gets even worse with the text lines of different orientations. Such lines are called as multi-skewed lines. These multi-skewed lines are easily observed in both printed and handwritten documents. It is a challenging task to design a real time system, which can maintain a high recognition rate with good accuracy and is independent of the type of documents and character fonts. In this paper, we attempt to analyze and classify...

In this paper, an analysis of the elapsed time and PSNR for encoding and decoding the videos in different sampling formats of YC B C R i.e. 4:4:4, 4:2:2 and 4:2:0 is proposed. The main algorithm of codec's is Motion-JPEG. The experimental result of comparison shows that the 4:2:0 format take less time for encoding as well as decoding and has comparable signal to noise ratio with that of 4:2:2 and 4:4:4 sampling formats for the same video. The work carried out has been tested for a number of videos taken with different sizes also with different number of frames and with different frame rates.