In this paper, a novel infrared maritime small target detection method, called local dissimilarity measure with anti interference based on global graph clustering (LDMGGC), is proposed. The Wasserstein distance is introduced to calculate the dissimilarity of gray level distribution between a central region and its neighborhoods. These dissimilarities construct the feature of a region. With this feature, detection for recalling all suspected targets is achieved. As the maritime interferences among suspected targets are able to be clustered, relaxing mutual k nearest neighbor graph is introduced in global graph clustering for filtering interferences. With this method, real targets are detected and maritime interferences are filtered out. Experiments are conducted on three maritime datasets and a non-maritime dataset for comparison. On three datasets, the proposed method achieves the best Receiver Operating Characteristic curves and Area Under Curve (0.99529, 0.99945, 0.99573, and 0.9906) values, meaning that the proposed method has high detection probability and low false-alarm ratio. Target Hit Rate (98.04%, 97.96%, 100%, and 99.24%) and Intersection of Union (0.8170, 0.7542, 0.5824, 0.7707) on four datasets of the proposed method show it has a strong ability to suppress the interferences

In the rapidly evolving image processing domain, transformers have emerged as powerful tools, yet significant challenges are encountered when they are applied to underwater image enhancement, such as visual disparity and computational inefficiency. Transformers do not have a unique module to maintain their performance while reducing the number of parameters. This study addresses the gap in the literature by introducing the globally deformable selection transformer (GS-Transformer), which is a model designed to enhance global feature selection and pixel connectivity, thereby reducing the computational complexity of the model while maintaining the image processing effect. Our novel multiresolution encoder-decoder module explicitly incorporates global information, overcoming the limitations of traditional transformers, whereas the multilocal coherence preserving loss (MCPL) mechanism ensures content integrity and coherence. Compared with the latest transform-based underwater image algorithms, this method is 15 times faster and utilizes only 41.7% (or approximately a half less) of the number of parameters. The experimental results on the UIEB, EUVP, and Synthesize datasets reveal that GS-Transformer achieves state-of-the-art performance in underwater image enhancement, with a reduced parameter number and improved efficiency, representing a significant advancement in the field. Our research will promote the application of the transformer in scenarios with high real-time performance.

A novel post-processing method, O2O (Online to Offline), to improve the result of shape retrieval is proposed in this paper. The essence of this proposed method is to move more work that consumes a lot of calculation to offline. With this essence, the O2O improves the retrieval result online with the help of the analysis offline. The offline analysis has two versions, one is self retrieval and the other is database clustering. The result of this kind of offline analysis can be reused indefinitely, regardless of the query shape, as long as the database is unchanged. Therefore, O2O is very efficient and suitable for real-time applications. This method is applied to shape retrieval and shape recognition with experiments on three databases, MPEG-7 CE1 Part B, Kimia 99 and Swedish Leaf. The results of the experiments in this paper show that O2O is not only efficient but also effective.

A novel network for enhancement of underwater optical images is proposed in this paper. It contains a Reinforcement Fusion Module for Haar wavelet (RFM-Haar) images. Fusion is performed to enrich available underlying information for better enhancement. As this network transform Haar Images into Fusion Images, it is called HIFI-Net. The experimental results based on Mean Square Error (0.1952, 0.1512 and 0.4683), Peak Signal to Noise Ratio (25.2241, 26.3342 and 21.4253) and Structure Similarity Index Measure (0.8265, 0.8819 and 0.8012) on three public datasets (EUVP, UFO-110 and UIEB) demonstrate that the proposed HIFI-Net performs better than some existing state-of-the-art methods.