InfoBoost for Selecting Discriminative Gabor Features

Mammography is currently the most effective imaging modality for early detection of breast cancer. In a CAD system for masses based on mammography, a mammogram is segmented to detect the masses. The segmentation gives rise to mass regions of interested (ROIs), which are either benign or malignant. There is a need to classify the extracted mass ROIs into benign and malignant masses; it is a hard problem because the texture micro-structures of benign and malignant masses have close resemblance. In this paper, a method for classifying mass ROIs into benign and malignant masses is presented. The key idea of the proposal is to build an ensemble classifier that employs Gabor features, consults different experts (classifiers) and takes the final decision based on majority vote. The system is evaluated on 512 (256 benign+256 malignant) mass ROIs extracted from mammograms of DDSM database. The ensemble classifier improves the classification rate for the problem of the discrimination of benign and malignant masses to 90.64%. Comparison with state-of-the-art techniques suggests that the proposed system outperforms similar methods.

Download Full-text

Shared and Independent Neural Representation Between Visual Perception and Mental Imagery

10.21203/rs.3.rs-788978/v1 ◽

2021 ◽

Author(s):

Yingying Huang ◽

Frank Pollick ◽

Ming Liu ◽

Delong Zhang

Keyword(s):

Visual Perception ◽

Mental Imagery ◽

Activity Patterns ◽

Neural Representation ◽

Gabor Features ◽

Visual Areas ◽

Neural Substrate ◽

Early Visual Cortex ◽

Human Participants ◽

Insight Into

Abstract Visual mental imagery and visual perception have been shown to share a hierarchical topological visual structure of neural representation. Meanwhile, many studies have reported a dissociation of neural substrate between mental imagery and perception in function and structure. However, we have limited knowledge about how the visual hierarchical cortex involved into internally generated mental imagery and perception with visual input. Here we used a dataset from previous fMRI research (Horikawa & Kamitani, 2017), which included a visual perception and an imagery experiment with human participants. We trained two types of voxel-wise encoding models, based on Gabor features and activity patterns of high visual areas, to predict activity in the early visual cortex (EVC, i.e., V1, V2, V3) during perception, and then evaluated the performance of these models during mental imagery. Our results showed that during perception and imagery, activities in the EVC could be independently predicted by the Gabor features and activity of high visual areas via encoding models, which suggested that perception and imagery might share neural representation in the EVC. We further found that there existed a Gabor-specific and a non-Gabor-specific neural response pattern to stimuli in the EVC, which were shared by perception and imagery. These findings provide insight into mechanisms of how visual perception and imagery shared representation in the EVC.

Download Full-text

Survei Penelitian Pengenalan Pola dalam Identifikasi Biometrik

Jurnal Telekomunikasi dan Komputer ◽

10.22441/incomtech.v7i1.1162 ◽

2017 ◽

Vol 7 (1) ◽

pp. 19

Author(s):

Regina Lionnie ◽

Mudrik Alaydrus

Keyword(s):

Local Binary Pattern ◽

Image Alignment ◽

Chi Square ◽

Histogram Matching ◽

Gabor Features ◽

Averaging Filter

Pengenalan pola memainkan peranan yang penting dalam identifikasibiometrik. Hal ini dikarenakan pengenalan pola dalam identifikasibiometrik membantu pihak berwenang dalam mengungkap identitasseorang kriminal. Pengenalan pola identifikasi biometrik dalam imageprocessing mencakup pengenalan pola wajah, geometri dari sebuahtangan, iris dan retina dari organ mata, sklera mata, pembuluh darah,tanda kulit dan rambut tubuh. Pengenalan pola identifikasi biometrikmembutuhkan metode pengenalan pola yang akurat, pemilihan tahap praproses dan metode klasifikasi yang sesuai. Pada survei paper ini dibahasmengenai beberapa metode tahap pra proses seperti Averaging Filter,Histogram, Desaturation, Binerisation dan Image Alignment. Metodepengenalan pola yang dibahas pada paper ini adalah Gabor Features,Local Binary Pattern, Local Gabor Binary Pattern dan Haar WaveletTransform. Sedangkan metode klasifikasi yang dibahas adalah Euclideandistance, Chi-square distance dan Histogram Matching. Agar dapatmemberikan hasil terbaik, setiap sistem pengenalan pola tidak dapatmenggunakan metode yang sama untuk mengenali pola identifikasibiometrik yang berbeda. Dibutuhkan penelitian dalam penggunaanmetode pra proses, ekstraksi fitur dan klasifikasi untuk setiap identifikasibiometrik yang ingin dikenali polanya.

Download Full-text