Session Program

Abstract - Color is a powerful feature for image analysis but it is usually not used in image classification schemes. We propose a method to combine fuzzy color information with the result obtained from a One-Versus-All classifier (OVA) trained with Bag-of-features. This method consists in weighting the outputs of the OVA classifier based on the distances between the new image to be classified and the classes. Experimental results show that our approach improves OVA classifier performance.

Abstract - While the Choquet integral (ChI) is a powerful parametric nonlinear aggregation function, it has limited scope and is not a universal function generator. Herein, we focus on a class of problems that are outside the scope of a single ChI. Namely, we are interested in tasks where different subsets of inputs require different ChIs. Herein, a genetic program (GP) is used to extend the ChI, referred to as GpChI hereafter, specifically in terms of compositions of ChIs and/or arithmetic combinations of ChIs. An algorithm is put forth to learn the different GP ChIs via genetic algorithm (GA) optimization. Synthetic experiments demonstrate GpChI in a controlled fashion, i.e., we know the answer and can compare what is learned to the truth. Real-world experiments are also provided for the mult-sensor fusion of electromagnetic induction (EMI) and ground penetrating radar (GPR) for explosive hazard detection. Our mutli-sensor fusion experiments show that there is utility in changing aggregation strategy per different subsets of inputs (sensors or algorithms) and fusing those results.

Abstract - Accurate image segmentation is an important issue in image processing, where unsupervised clustering models play an important part and have been proven to be effective. However, most clustering methods suffer from limited segmentation accuracy without considering spatial information or bounded support region for practical data. In this paper, a bounded spatial probability based fuzzy clustering algorithm is proposed for image segmentation. A bounded distribution to fit the bounded data is utilized and a new conditional probability is constructed based on the immediate neighboring probabilities. Then a parameter-free mean template is presented to impose the spatial information more precisely. Finally, the negative logarithmical conditional probability is utilized as the dissimilarity function to describe the observed data. We evaluated our algorithm against several state-of-the-art segmentation approaches on brain magnetic resonance images. Our results suggest that the proposed algorithm is more robust to noise and textures, and can produce more accurate segmentation results.

Abstract - This paper proposes a new approach for single frame image super resolution using multiple ANFIS (Adaptive Network-based Fuzzy Inference System) mappings. It presents an implemented learning system that captures the relationship between a low resolution (LR) image patch space and a high resolution (HR) one given an external image database. In particular, a collected large number of LR and HR image patch pairs are divided into different groups with a clustering method. For each clustered group of the training samples, an ANFIS mapping is learned for super resolution (SR). The non- local means filter is subsequently employed to suppress the displeasing artefacts of the resulting reconstructed HR image. The proposed approach is evaluated on a range of natural images and compared with a number of existing state-of-the-art SR algorithms, demonstrating its effectiveness.

Abstract - The analysis of the perceptual properties of texture plays a fundamental role in tasks where some interaction with subjects is needed. In order to face the imprecision related to these properties, several fuzzy approaches can be found in the literature, but they do not properly take into account the subjectivity of users. In this paper, a generic technique is proposed in order to adapt any multidimensional fuzzy set to the different perceptions of texture properties that a particular user can have. This way, we combine the improvement in the texture characterization given by the use of several computational measures as reference set with the adaptation to the subjectivity of the human perception. In the proposed adaptation method, the membership functions are automatically transformed on the basic of the information given by the user.