Indu Sreedevi

NGFICA Based Digitization of Historic Inscription Images

This paper addresses the problems encountered during digitization and preservation of inscriptions such as perspective distortion and minimal distinction between foreground and background. In general inscriptions possess neither standard size and shape nor colour difference between the foreground and background. Hence the existing methods like variance based extraction and Fast ICA based analysis fail to extract text from these inscription images. Natural gradient flexible ICA (NGFICA) is a suitable method for separating signals from a mixture of highly correlated signals, as it minimizes the dependency among the signals by considering the slope of the signal at each point. We propose an NGFICA based enhancement of inscription images. The proposed method improves word and character recognition accuracies of the OCR system by 65.3% (from 10.1% to 75.4%) and 54.3% (from 32.4% to 86.7%), respectively.

Enhancement of inscription images

This paper addresses the problems encountered during digitization and preservation of inscriptions such as perspective distortion and minimal distinction between foreground and background. In general inscriptions neither possess standard size and shape nor colour difference between the foreground and background. Hence the existing methods like variance based extraction and Fast-ICA based analysis fail to extract text from these inscription images. Natural gradient Flexible ICA (NGFICA) is a suitable method for separating signals from a mixture of highly correlated signals, as it minimizes the dependency among the signals by considering the slope of the signal at each point. We propose an NGFICA based enhancement of inscription images. The proposed method improves word and character recognition accuracies of the OCR system by 65.3% (from 10.1% to 75.4%) and 54.3% (from 32.4% to 86.7%) respectively.

Real-Time Distributed Multi-object Tracking in a PTZ Camera Network

A visual surveillance system should have the ability to view an object of interest at a certain size so that important information related to that object can be collected and analyzed as the object moves in the area observed by multiple cameras. In this paper, we propose a novel framework for real-time, distributed, multi-object tracking in a PTZ camera network with this capability. In our framework, the user is provided a tool to mark an object of interest such that the object is tracked at a certain size as it moves in the view of various cameras across space and time. The pan, tilt and zoom capabilities of the PTZ cameras are leveraged upon to ensure that the object of interest remains within the predefined size range as it is seamlessly tracked in the PTZ camera network. In our distributed system, each camera tracks the objects in its view using particle filter tracking and multi-layered belief propagation is used for seamlessly tracking objects across cameras.

Bio-Inspired Distributed Sensing Using a Self-Organizing Sensor Network

Nature offers several examples of self-organizing systems that automatically adjust to changing conditions without adversely affecting the system goals. We propose a self-organizing sensor network that is inspired from real-life systems for sampling a region in an energy-efficient manner. Mobile nodes in our network execute certain rules by processing local information. These rules enable the nodes to divide the sampling task in a manner such that the nodes self-organize themselves to reduce the total power consumed and improve the accuracy with which the phenomena are sampled. The digital hormone-based model that encapsulates these rules, provides a theoretical framework for examining this class of systems. This model has been simulated and implemented on cricket motes. Our results indicate that the model is more effective than a conventional model with a fixed rate sampling.

An optimal underwater image enhancement based on fuzzy gray world algorithm and Bacterial Foraging algorithm

Underwater images suffer from non uniform contrast and poor visibility due to bad illumination and color cast in deep water. Such images have a hazy and color diminished appearance making underwater studies a difficult task. Researches in last decades performed color correction, assuming that underwater images have bluish color cast which is not always true. In this paper, a new image enhancement approach is proposed which modifies the gray world algorithm by finding the color cast using fuzzy logic and then removing the color cast by optimizing the correction method using Bacterial Foraging Optimisation (BFO). Proposed approach is adaptive in nature as it finds the intensity of color cast instead of assuming it which improves the quality of underwater images. Computed results have enhanced visual details, contrast and color performance.

Processing of Historic Inscription Images

The study and analysis of epigraphy is important for knowing about the past. From around third century to modern times, about 90,000 inscriptions have been discovered from different parts of India.

Robust pedestrian tracking using improved tracking-learning-detection algorithm

Manual analysis of pedestrians for surveillance of large crowds in real time applications is not practical. Tracking-Learning-Detection suggested by Kalal, Mikolajczyk and Matas [1] is one of the most prominent automatic object tracking system. TLD can track single object and can handle occlusion and appearance change but it suffers from limitations. In this paper, tracking of multiple objects and estimation of their trajectory is suggested using improved TLD. Feature tracking is suggested in place of grid based tracking to solve the limitation of tracking during out of plane rotation. This also leads to optimization of algorithm. Proposed algorithm also achieves auto-initialization with detection of pedestrians in the first frame which makes it suitable for real time pedestrian tracking.