Code Projects

2014

Handwritten Signature Based Human Psychology Prediction using Time Series Analysis:

In this, human signatures are used to perform user identification and signature verification. The time series technology is used here for spatial to frequency conversion which is analyzed using min-max DST co-efficient. The co-efficient are used for classification using k-NN classifier. The analysis also results in human signature sub-classification predicting the mental state of human while he/she was signing. With a great success the task was completed but needs more enhancements. Matlab and WEKA tools are used for this study.

In this, a novel method to convert a grayscale image to a colored image for quality image analysis is proposed. The grayscale IP operations are very challenging and limited. Therefore, information extracted from such images are inaccurate and so the input images are transformed to a colored image using a reference color image by applying reverse engineering. The gray levels of grayscale image are mapped with the color image in all the three layers (red, green, blue). The algorithm is very simple and accurate that it can be used in any domain such as medical imaging, satellite imaging and agriculture/environment real-scene. The algorithms are implemented and tested on low cost mobile devices too.

2013

Brain Tumor Segmentation and Visualization in 3D Volumetric Data:

Improved automated region growing approach to detect brain tumor from a volumetric FLAIR MR images. This project focuses on multiple thresholding techniques to obtain suitable seed points for region grow algorithm to accurately segment the tumor and visualize it in a 3D volume. VTK and ITK are used to process the data and hand data glove is used to interact with it.

An automated intelligent mobile vision based technique for extracting principal lines from colored images of human palm to predict the personality of users. A robust and efficient algorithm is designed to work on low processing devices such as mobile phones with low resolution camera. A mobile client-server architecture is involved in this project.Winner of national Student Project Contest at Intelligent Interactive Technologies and Multimedia (IITM 2013), IIIT Allahabad.Second runner up at IBM I-CARE 2013, IBM Research Center, New Delhi.

Most of the diseases in plants have their visual effect on leaves- changes in color, spots formation, and variation in shape and in patterns of vein diagram, etc. The project focuses to match the image of the test leaf with the dataset collection by using several feature extraction and matching algorithms (GABOR WAVELET and SUPPORT VECTOR MACHINE respectively).2011

The project aimed at making a graphics to show the satellite view of the IIITA as it looks on the globe. It is used to know the detailed information about the IIIT and the more IIITA. It mainly focused on the use of 3D graphics library, OpenGL.

This project aimed on the attendance system using the face recognition techniques. A capturing device was used to capture the face of the faculties and the students and used to mark the attendance on the daily basics in respect to time.2008

This was a detailed study of ATM machine software and its working. It was aimed at having an online canteen bill payment form the student account in the college. The language used was java.

Casio is a graphics project focusing mainly on the 2-D graphics. It used Turbo C.3.0 2-D graphics library to make a Casio which is played by the use of the keyboard.

Won first prize in national technical coding fest at IILM.