Rotation-invariant texture image retrieval using particle swarm optimization and support vector regression

- A rotation-invariant texture image retrieval technique adopts the PSO and the SVR.
- LPM-FFT, Gabor filter, and Zernike moment are utilized to extract image features.
- The PSO algorithm is utilized to select a nearly optimal parameter set for the technique.
- The technique uses the SVR to promote its image-retrieval efficiency.
- The technique outperforms other existing rotation-invariant image retrieval methods.