As there are countless significant works done for handwritten character recognition, very meager effort has been reported for inscription characters especially for Tamil stone inscriptions. The real challenge faced in handling stone inscription is dataset collection and foreground and background discrimination. Till present days, the archeological department follows traditional way of capturing, preserving and deciphering stone inscriptions which is manual, more time consuming and need expert assistance. Hence digitized recognition is essential and efficient pattern matching algorithm is needed to be developed to deal with variations in shape and size of complex structured characters present in Tamil stone inscriptions. In this paper, an automated character recognition by pattern matching approach is developed, where character features were extracted by using pattern matching algorithm that helps achieving good recognition rate. Recognition of ancient Tamil stone inscriptions characters and finding their corresponding contemporary Tamil character is done by Image-based Character Pattern Identification (ICPI) system. Modified Speeded Up Robust Feature with Bag of Grapheme (MSURF-BoG) algorithm is implemented to detect the strongest key points from the input character with different orientations. These key point features were created for training the image as a model called Bag of Grapheme (BoG) with code word creation. Hence unsupervised key point features were extracted and pattern matching is performed. 11th century Tamil stone inscriptions were taken as samples which has 7 vowels and 17 consonants, totally 24 characters were used. Here samples with different orientation from each 24 character were used for training the system. The proposed system is evaluated by recognition accuracy which is reported for character wise at the maximum of 96%.

Background: Universally, the most predominant cause of female mortality is mainly due to breast cancer. Owing to numerous constraints in the existing imaging technique, researchers are trying out an alternative tool to detect the tumor before going to the miserable stage. Methods: This article presents a novel method to detect the mean value system for detecting the location of the tumor in different depths by shifting the antenna anywhere in the breast tissue. In addition, an algorithm to reconstruct the breast image, namely Delay-Multiply-and-Sum (DMAS) is followed to identify the tumor implanted in the breast tissue. Results: The analysis shows that the maximum mean value occurs while the antenna moves very near to the tumor while the mean value reduces while the antenna shifts apart from the tumor location. The mean value in different locations is converted into a microwave image. The high intensity in the image exhibits the precise position of the tumor. This technique can identify the location of early-stage tumor of size 3mm. Multiple tumors of sizes 6mm and 7mm can identify at a depth of 12mm and 18mm in the homogeneous breast phantom. DMAS can provide better imaging results in the early stage tumor of size 3mm embedded in the breast phantom. Conclusion: Microwave imaging is an efficient technique to differentiate healthy and malignant tissue in the breast. Antenna plays a major role in identifying tumors in the breast in the early stage. Hence a high-performance Ultra Wideband Dielectric Resonator Antenna (DRA-UWB) is used to identify the tumor in the breast. An antenna is sketched in different locations of the breast phantom. On account of the hemispherical structure, the mean value of the reflected signal is high at the center than at the edge. Hence, the difference in mean value is calculated with and without breast phantom for identifying the tumor location. The overall efficiency of this technique can be improved by using a high-performance UWB antenna. The image of the breast is reformed by the DMAS beamforming algorithm.

Most of the ancient historical inscriptions and other forms of textual data were written in Brahmi. These inscriptions include details about historical figures and occasions in Indian history about which no other information is available. Brahmi serves as the base script for many languages in south Asian countries including Tamil. Temple epigraphy have long been preserved as physical estampage that are bound to deterioration. So far, no work initiated for digitization and transliterate stone inscriptions, those inscriptions were preserved only in the form of printed record. This makes digitization of the stone inscriptions important. The digitization of stone carved characters deals with more preprocessing and noise removal techniques. Unlike handwritten or printed documents, the stones and temple walls almost exhibit the same color as foreground and background which makes the feature extraction more difficult. This paper uses Python OpenCV library for converting the stone images into binarized (black background and white characters) form. It is important to transliterate the Brahmi characters into some other language since these symbols doesn’t make any sense to the present world. Tamil is one of the oldest languages continuously spoken today, and it has a wealth of literature which consists of 12 vowels, 18 consonants, 216 compound characters and 1 special character (Ayutha ezhuthu). Hence the recognized Brahmi characters are transliterated into contemporary Tamil through Tesseract Optical Character Recognition (OCR) with an accuracy of 85%