A comparative analysis of the Zernike moments for single object retrieval

العناوين الأخرى

تحليل مقارن للحظات زينرك لاسترجاع كائن منفرد

المؤلفون المشاركون

Abu Bakar, Thurayya
Yusuf, Wan Nural Jawahir Hj Wan
Hitam, Muhammad Suzuri

المصدر

Baghdad Science Journal

الناشر

جامعة بغداد كلية العلوم للبنات

تاريخ النشر

2019-06-30

دولة النشر

العراق

عدد الصفحات

11

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

الملخص الإنجليزي

Zernike Moments has been popularly used in many shape-based image retrieval studies due to its powerful shape representation.

However its strength and weaknesses have not been clearly highlighted in the previous studies.

Thus, its powerful shape representation could not be fully utilized.

In this paper, a method to fully capture the shape representation properties of Zernike Moments is implemented and tested on a single object for binary and grey level images.

The proposed method works by determining the boundary of the shape object and then resizing the object shape to the boundary of the image.

Three case studies were made.

Case 1 is the Zernike Moments implementation on the original shape object image.

In Case 2, the centroid of the shape object image in Case 1 is relocated to the center of the image.

In Case 3, the proposed method first detect the outer boundary of the shape object and then resizing the object to the boundary of the image.

Experimental investigations were made by using two benchmark shape image datasets showed that the proposed method in Case 3 had demonstrated to provide the most superior image retrieval performances as compared to both the Case 1 and Case 2.

As a conlusion, to fully capture the powerful shape representation properties of the Zernike moment, a shape object should be resized to the boundary of the image.

نوع البيانات

أوراق مؤتمرات

رقم السجل

BIM-891235

• APA
• MLA
• AMA