Image Retrieval Based on the Combination of Region and Orientation Correlation Descriptors

Table 2

Retrieval results of CROCD in different color spaces for Corel-1K dataset.

Color space		Precision (%)					Recall (%)
		10	15	20	25	30	10	15	20	25	30
HSV	72 (nonuniform)	83.20	78.07	74.60	71.96	69.80	8.320	11.71	14.92	17.99	20.94
	72	80.60	77.60	73.75	70.56	68.77	8.060	11.64	14.75	17.64	20.63
	108	79.50	74.73	71.45	68.80	67.07	7.950	11.21	14.29	17.20	20.12
	128	81	75.80	72.90	70.40	68.03	8.100	11.37	14.58	17.60	20.41
	192	78.70	73.93	71.15	69.24	67.27	7.870	11.09	14.23	17.31	20.18
RGB	16	72.90	68.13	65.10	62.20	59.70	7.290	10.22	13.02	15.55	17.91
	32	79.20	74.74	71.55	68.48	66.43	7.920	11.21	14.31	17.12	19.93
	64	77.90	73.93	70.25	67.48	65.20	7.790	11.09	14.05	16.87	19.56
	128	78.50	74.47	70.60	67.92	65.57	7.850	11.17	14.12	16.98	19.67
Lab	45	64.50	60.80	57	54.60	51.67	6.450	9.120	11.40	13.65	15.50
	90	71.50	65.47	62.10	59.24	56.67	7.150	9.820	12.42	14.81	17
	180	69.70	65.33	61.90	59.64	57.13	6.970	9.800	12.38	14.91	17.14
	225	69.80	65.13	62.30	59.52	57.10	6.980	9.770	12.46	14.88	17.13

The best retrieval results are shown in bold, which means that CROCD has the best performance on this condition.