Krishna Dharavath ¹, Fazal Ahmed Talukdar ¹, Rabul Hussain Laskar ¹

Affiliations
1 Speech and Image Processing Research Lab, Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Assam-788010, IN

Abstract

Quality of image plays a vital role in increasing face recognition rate. A good quality image gives better recognition rate than noisy images. It is more difficult to extract features from such noisy images which in-turn reduces face recognition rate. To overcome problems occurred due to low quality image, pre-processing is done before extracting features from the image. In this paper we will analyze the effect of pre-processing prior to feature extraction process with respect to the face recognition rate. This also gives a qualitative description of various pre-processing techniques and feature extraction schemes that were used for our analysis. The results were analyzed with the help of bar graphs. The combined method of feature extraction (Spatial and Frequency) shows superior performance than individual feature extraction schemes. Also, this combined method gives good recognition results even without pre-processing of the image.

Keywords

Comparative Study, Face Recognition, Frequency Feature, Image Preprocessing, Image Quality, Spatial Feature

Full Text

   

Salam Shuleenda Devi ¹, Shah Alam Sheikh ², Anuradha Talukdar ³, Rabul Hussain Laskar ¹

Affiliations
1 Department of Electronics and Communication Engineering, National Institute of Technology, Silchar, Assam –788010, IN
2 Department of Pathology, Silchar Medical College and Hospital, Silchar, Assam – 788014, IN
3 Cachar Cancer Hospital and Research Centre, Silchar, Assam – 788015, IN

Abstract

Objectives: This paper aims to develop a system for malaria infected erythrocyte classification based on the histogram feature set. Method: The method consist of pre-processing, segmentation, feature extraction based on the histogram of different color channels, feature selection and malaria infected erythrocyte classification using Artificial Neural Networks (ANN), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Naive Bayes. Findings: The experimental analysis of all the classifiers with the different combinations of features has been carried out on clinical database. Based on the experimental results it may be concluded that ANN provides the higher classification rate in comparison to other classifiers which provides an overall accuracy of 96.32% and F-score of 85.32% respectively. Applications: The proposed system may be used for the automatic recognition of the malaria infected erythrocytes in the thin blood smears.

Keywords

Erythrocyte, Histogram Features, Malaria, Microscopic Image, Thin Blood Smears.

Full Text