MACHINE LEARNING OF HANDWRITTEN NANDINAGARI CHARACTERS USING VLAD VECTORS
Journal Title: ICTACT Journal on Image and Video Processing - Year 2017, Vol 8, Issue 2
Abstract
This paper provides an early attempt to train and retrieve handwritten Nandinagari characters using one of the latest techniques in visual feature detection. The data set consists of over 1600 handwritten Nandinagari characters of different fonts, size, rotation, translation and image formats. In the Learning phase, we subject them to an approach where their recognition is effective by first extracting their key interest points on the images which are invariant to Scale, rotation, translation, illumination and occlusion. The technique used for this phase is Scale Invariant Feature Transform (SIFT). These features are represented in quantized form as visual words in code book generation step. Then the Vector of Locally Aggregated Descriptors (VLAD) is used for encoding each of the Image descriptors in the database. In the recognition phase, for query image, SIFT features are extracted and represented as query vector .Then these features are compared against the visual vocabulary generated by code book to retrieve similar images from the database. The performance is analysed by computing mean average precision .This is a novel scalable approach for recognition of rare handwritten Nandinagari characters with about 98% search accuracy with a good efficiency and relatively low memory usage requirements.
Authors and Affiliations
Prathima Guruprasad, Jharna Majumdar
Keywords
Related Articles
- EP ID EP388657
- DOI 10.21917/ijivp.2017.0229
- Views 79
- Downloads 0
PERFORMANCE ANALYSIS OF AUDIO AND VIDEO SYNCHRONIZATION USING SPREADED CODE DELAY MEASUREMENT TECHNIQUE
The audio and video synchronization plays an important role in speech recognition and multimedia communication. The audio-video sync is a quite significant problem in live video conferencing. It is due to use of various...
COMPARISON OF CONTOUR FEATURE BASED AND INTENSITY BASED INSAT-3D MET IMAGES COREGISTRATION FOR SUB PIXEL ACCURACIES
Image registration in meteorological images that are acquired continuously for their use in weather forecast activities and other related scientific analysis is a critical requirement. Meteorological images are obtained...
AN ENHANCED MAMMOGRAM DIAGNOSIS USING SHIFT-INVARIANT TRANSFORM
Breast cancer is a common disease for women and various techniques have been used to detect the breast cancer. The mammogram images are noise, low contrast and blur due to limitations of the X-ray hardware system. So, we...
PERFORMANCE IMPROVEMENT OF IDMA SCHEME USING CHAOTIC MAP INTERLEAVERS FOR FUTURE RADIO COMMUNICATION
In this paper, chaos based interleavers are proposed for the performance improvement of Interleave Division Multiple Access (IDMA henceforth) for future radio communication (FRC) requirements. ‘IDMA’ can be mean as the m...
USAGE OF BIOINFORMATIC DATA FOR REMOTE AUTHENTICATION IN WIRELESS NETWORKS
Authentication is the step to approve the correctness of an attribute of a individual or entity group. Sensitive information might help in making the authentication. Regularly this encrypted information is processed via...