Image retrieval technique using the clustering based on rearranged radon transform

This study proposed a new image retrieval technique in which the existing radon transform that was used for image retrieval is reinforced with noise invariance. For this, a radon transform was performed on an inquiry image which had been preprocessed to extract vector values and then the vector values were arranged depending on size to extract a second feature vector. After clustering and normalizing the levels of vector values based on the second feature vector, the feature vector was created. For a simulation on the image retrieval technique using the clustering based on rearranged radon transform, diverse images were used in this experiment. For performance analysis, the system proposed was compared with the retrieval system using a rearrangement hough transform based on voting number. As a result, the proposed image retrieval technique was more robust to geometric transforms such as rotated and scaled in the retrieval technique using the general radon transform and standard hough transform, and it had recall enhanced to 0.05 and precision enhanced to 0.04 in comparison with the rearrangement hough transform based on voting number.