Characterizing Global Hand-Crafted Feature Descriptors for Sketch-Based Image Retrie

被引：0
|
作者：
Abbas, Mohd Hussaini [1 ]
Ani, Adi Izhar Che [1 ]
Abd Samat, Ahmad Asri [1 ]
Hazim, Muhamad Amirul [1 ]
Kader, Mohamed Mydin M. Abdul [2 ]
Setumin, Samsul [1 ]
Hamidi, Mohd [1 ]
机构：
[1] Univ Teknol MARA, Fac Elect Engn, Cawangan Pulau Pinang, Permatang Pauh 13500, Pulau Pinang, Malaysia
[2] Univ Malaysia Perlis, Fac Elect Engn Technol, Campus Pauh Putra, Arau 02600, Perlis, Malaysia
来源：
6TH IEEE INTERNATIONAL CONFERENCE ON RECENT ADVANCES AND INNOVATIONS IN ENGINEERING (ICRAIE) | 2021年
关键词：
feature extraction; SBIR; HOG; Gabor and LBP;
D O I：
10.1109/ICRAIE52900.2021.9703823
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
Sketch-based Image Retrieval (SBIR) is an essential method of searching objects by drawing them in two-dimensional (2-D). The SBIR problem was that the image inside the dataset did not match the pair due to its modality difference. The main objective of this research is to compare which descriptor is better adapted to the SBIR. Histogram of Oriented Gradient (HOG), Gabor, and Local Binary Pattern (LBP) are selected for the study. Each sample will be divided into distance measures with features vector that corresponds to the training dataset will be compared the performance in order to study the best adapted to SBIR. Histogram of Oriented Gradient (HOG) is identified as the best descriptor for SBIR. HOG has shown a better performance than Gabor and LBP since the method shows the highest percent of distance matrices accuracy.
引用
收藏
页数：4
相关论文
共 50 条
  • [1] A Comparison of CNN-Based and Hand-Crafted Keypoint Descriptors
    Dai, Zhuang
    Huang, Xinghong
    Chen, Weinan
    He, Li
    Zhang, Hong
    2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2019, : 2399 - 2404
  • [2] Hand-Crafted vs Learned Descriptors for Color Texture Classification
    Napoletano, Paolo
    COMPUTATIONAL COLOR IMAGING, CCIW 2017, 2017, 10213 : 259 - 271
  • [3] Length Independent Writer Identification Based on the Fusion of Deep and Hand-Crafted Descriptors
    Sulaiman, Alaa
    Omar, Khairuddin
    Nasrudin, Mohammad F.
    Arram, Anas
    IEEE ACCESS, 2019, 7 : 91772 - 91784
  • [4] Learned BRIEF - transferring the knowledge from hand-crafted to learning-based descriptors
    Zizakic, Nina
    Pizurica, Aleksandra
    2020 IEEE 22ND INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2020,
  • [5] Feature detection and description for image matching: from hand-crafted design to deep learning
    Chen, Lin
    Rottensteiner, Franz
    Heipke, Christian
    GEO-SPATIAL INFORMATION SCIENCE, 2021, 24 (01) : 58 - 74
  • [6] Fusion of Deep Feature and Hand-Crafted Features for Terrain Recognition
    Li, Xue
    Ma, Xin
    Song, Peng
    2019 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE APPLICATIONS AND TECHNOLOGIES (AIAAT 2019), 2019, 646
  • [7] Combining CNN with Hand-Crafted Features for Image Classification
    Zhou Tianyu
    Miao Zhenjiang
    Zhang Jianhu
    PROCEEDINGS OF 2018 14TH IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP), 2018, : 554 - 557
  • [8] An Interpretable Hand-Crafted Feature-Based Model for Atrial Fibrillation Detection
    Rouhi, Rahimeh
    Clausel, Marianne
    Oster, Julien
    Lauer, Fabien
    FRONTIERS IN PHYSIOLOGY, 2021, 12
  • [9] Image Matching Based on Trusted Feature in Sketch-based Retrieval
    Wu, Jian-jie
    Wu, Tao
    Yue, Yan
    Li, Xiao-long
    Tan, Yan-jie
    Wang, Xiao-chen
    INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ARTIFICIAL INTELLIGENCE (ICCSAI 2014), 2015, : 14 - 18
  • [10] Hand-Crafted Feature Offset Learning for Tumor Segmentation in PET
    Liu, S.
    Tan, X.
    Zhao, X.
    Li, L.
    Lu, W.
    Tan, S.
    MEDICAL PHYSICS, 2018, 45 (06) : E397 - E397
12345