Similarity Guided Learning of the Case Description and Improvement of the System Performance in an Image Classification System

2002 ◽  
pp. 604-612 ◽  
Author(s):  
Petra Perner ◽  
Horst Perner ◽  
Bernd Müller
Keyword(s):  
Image Classification ◽  
Classification System ◽  
System Performance ◽  
Case Description ◽  
Guided Learning

A Fuzzy Matching based Image Classification System for Printed and Handwritten Text Documents

2020 ◽  
Vol 13 (2) ◽  
pp. 155-194
Author(s):  
Shalini Puri ◽  
Satya Prakash Singh
Keyword(s):  
Image Classification ◽  
Classification System ◽  
Word Association ◽  
Computation Time ◽  
Document Classification ◽  
Efficient Manner ◽  
Text Documents ◽  
Handwritten Text ◽  
Fuzzy Matching ◽  
Character Classification

This article proposes a bi-leveled image classification system to classify printed and handwritten English documents into mutually exclusive predefined categories. The proposed system follows the steps of preprocessing, segmentation, feature extraction, and SVM based character classification at level 1, and word association and fuzzy matching based document classification at level 2. The system architecture and its modular structure discuss various task stages and their functionalities. Further, a case study on document classification is discussed to show the internal score computations of words and keywords with fuzzy matching. The experiments on proposed system illustrate that the system achieves promising results in the time-efficient manner and achieves better accuracy with less computation time for printed documents than handwritten ones. Finally, the performance of the proposed system is compared with the existing systems and it is observed that proposed system performs better than many other systems.

scholarly journals Perbandingan Ekstraksi Fitur dan Proses Matching pada Autentikasi Sidik Jari Manusia

2020 ◽  
Vol 8 (1) ◽  
pp. 95
Author(s):  
ANGGUNMEKA LUHUR PRASASTI ◽  
BUDHI IRAWAN ◽  
SETIO EKA FAJRI ◽  
ANANDA RENDIKA ◽  
SUGONDO HADIYOSO
Keyword(s):  
Classification System ◽  
System Performance ◽  
Cross Correlation ◽  
Index Finger ◽  
Phase Correlation ◽  
Normalized Cross Correlation ◽  
Finger Vein ◽  
Maximum Curvature ◽  
Biometric Systems ◽  
Finger Recognition

ABSTRAK Sidik jari merupakan biometrik yang sering digunakan dalam teknologi autentikasi. Terdapat banyak metode yang bisa digunakan untuk membuat sistem klasifikasi sidik jari. Maximum Curvature Points (MCP) umumnya digunakan untuk ekstraksi citra pembuluh darah jari yang juga digunakan sebagai autentikasi. Pada penelitian ini akan diuji performansi dari metode MCP jika dibandingkan dengan metode yang umum digunakan pada proses pengenalan sidik jari, yaitu Hit and Miss Transform (HMT). Perbedaan domain, yaitu spasial pada Normalized Cross Correlation (NCC) dan frekuensi pada Phase Correlation (PC) dalam proses matching ternyata juga mempengaruhi performansi sistem. Hasilnya menunjukkan bahwa penggunakaan metode MHTNCC memiliki tingkat akurasi yang lebih baik dalam pengenalan sidik jari yaitu 92% untuk pengenalan ibu jari dan 98% untuk pengenalan jari telunjuk, dibandingkan dengan menggunakan metode MCP-PC yang hanya memiliki tingkat akurasi sebesar 88% untuk pengenalan ibu jari dan 92% untuk pengenalan jari telunjuk. Kata kunci: sidik jari, MCP, HMT, phase correlation, normalized cross correlation ABSTRACT Fingerprint is one of the biometric systems that are often used in an authentication technology. There are many methods that can be used to develop fingerprint’s classification system. Maximum Curvature Points (MCP) are generally used for finger vein image extraction which is also used as authentication. MCP performance will be compared to common method in finger print recognition, Hit and Miss Transform (HMT). Using different domains, spatial in Normalized Cross Correlation (NCC) and frequency in Phase Correlation (PC) affect the system performance. The results show that the application of HMT-NCC more accurate in terms of finger print’s recognition, 92% in accuracy for thumb recognition and 98% accuracy for index finger recognition, while MCP-PC is only reach 88% in accuracy for thumb recognition and 92% accuracy for index finger recognition. Keywords: fingerprint, MCP, HMT, phase correlation, normalized cross correlation

scholarly journals Classification of Low-Grade and High-Grade Glioma from MR Brain Images Using Multiple-Instance Learning with Combined Feature Set

2021 ◽  
pp. 1-24
Author(s):  
C. C. Benson ◽  
V. L. Lajish ◽  
Kumar Rajamani
Keyword(s):  
Image Classification ◽  
Classification System ◽  
Multiple Instance Learning ◽  
Low Grade ◽  
High Grade ◽  
Brain Images ◽  
Mr Brain Images ◽  
Combined Feature ◽  
Mr Brain

Fully automatic brain image classification of MR brain images is of great importance for research and clinical studies, since the precise detection may lead to a better treatment. In this work, an efficient method based on Multiple-Instance Learning (MIL) is proposed for the automatic classification of low-grade and high-grade MR brain tumor images. The main advantage of MIL-based approach over other classification methods is that MIL considers an image as a group of instances rather than a single instance, thus facilitating an effective learning process. The mi-Graph-based MIL approach is proposed for this classification. Two different implementations of MIL-based classification, viz. Patch-based MIL (PBMIL) and Superpixel-based MIL (SPBMIL), are made in this study. The combined feature set of LBP, SIFT and FD is used for the classification. The accuracies of low-grade–high-grade tumor image classification algorithm using SPBMIL method performed on [Formula: see text], [Formula: see text] and FLAIR images read 99.2765%, 99.4195% and 99.2265%, respectively. The error rate of the proposed classification system was noted to be insignificant and hence this automated classification system could be used for the classification of images with different pathological conditions, types and disease statuses.

Sign in / Sign up

Export Citation Format

Share Document