Use this URL to cite or link to this record in EThOS:
Title: Similarity measures for object matching in computer vision
Author: Kwon, Ohkyu
ISNI:       0000 0004 5914 6151
Awarding Body: University of Bolton
Current Institution: University of Bolton
Date of Award: 2016
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Restricted access.
Access from Institution:
The similarity measures for object matching and their applications have been important topics in many fields of computer vision such as those of image recognition, image fusion, image analysis, video sequence matching, and so on. This critical commentary presents the efficiency of new metric methods such as the robust Hausdorff distance (RHD), the accurate M-Hausdorff distance (AMHD), and the fast sum of absolute differences (FSAD). The RHD measure computes the similarity distance of the occluded/noisy image pair and evaluates the performances of the multi-modal registration algorithms. The AMHD measure is utilised for aligning the pair of the occluded/noisy multi-sensor face images, and the FSAD measure in adaptive-template matching method finds the zero location of the slide in an automatic scanning microscope system. A Hausdorff distance (HD) similarity measure has been widely investigated to compare the pair of two-dimensional (2-D) images by low-level features since it is simple and insensitive to the changes in an image characteristic. In this research, novel HD measures based on the robust statistics of regression analysis are addressed for occluded and noisy object matching, resulting in two RHD measures such as M-HD based on the M-estimation and LTS-HD based on the least trimmed squares (LTS). The M-HD is extended to three-dimensional (3-D) version for scoring the registration algorithms of the multi-modal medical images. This 3-D measure yields the comparison results with different outlier-suppression parameters (OSP) quantitatively, even though the Computed Tomography (CT) and emission-Positron Emission Tomography (PET) images have different distinctive features. The RHD matching technique requires a high level of complexity in computing the minimum distance from one point to the nearest point between two edge point sets and searching for the best fit of matching position. To overcome these problems, the improved 3×3 distance transform (DT) is employed. It has a separable scan structure to reduce the calculation time of the minimum distance in multi-core processors. The object matching algorithm with hierarchical structures is also demonstrated to minimize the computational complexity dramatically without failing the matching position. The object comparison between different modality images is still challenging due to the poor edge correspondence coming from heterogeneous characteristics. To improve the robustness of HD measures in comparing the pair of multi-modal sensor images, an accurate M-HD (AMHD) is proposed by utilizing the orientation information of each point in addition to the DT map. This similarity measure can precisely analyse the non-correspondent edges and noises by using the distance orientation information. The AMHD measure yields superior performance at aligning the pairs of multi-modal face images over those achieved by the conventional robust HD schemes. The sum of absolute differences (SAD) is popular similarity measure in template matching technique. This thesis shows the adaptive-template matching method based on the FSAD for accurately locating the slide in automated microscope. The adaptive-template matching method detects the fiduciary ring mark in the slide by predicting the constant used in the template, where the FSAD reduces the processing time with a low rate of error of the template matching by inducing 1-D vertical and horizontal SAD. The proposed scheme results in an accurate performance in terms of detecting the ring mark and estimating the relative offset in slide alignment during the on-line calibration process.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available