SOM competition for complex image scene with variant object positions
نویسندگان
چکیده
In this paper, a new SOM competition algorithm is proposed for image recognition applications. The competition in this algorithm depends on a subset of most discriminate weights of the network codebooks. This indeed can reduce the required recognition time of one image. In addition, the competition is applied on the pixels corresponding to the object gray levels only, this allows recognizing complex images with different lighting conditions. Furthermore, to allow shift variations in the position of the input object, window-based competition is proposed. Where, different subset windows are selected from the input image, then the competition is applied between each window and window of the same size in the center of the codebook of all feature map neurons. The experimental results of the new algorithm showed good performance in recognizing gestures of complex images with variant object position while the normal SOM competition algorithm completely failed.
منابع مشابه
Image Enhancement via Reducing Impairment Effects on Image Components
In this paper, a new approach is presented for improving image quality. It provides a new outlook on how to apply the enhancment methods on images. Image enhancement techniques may deal with the illumination, resolution, or distribution of pixels values. Issues such as the illumination of the scene and reflectance of objects affect on image captures. Generally, the pixels value of an image is ...
متن کاملScene perception: inferior temporal cortex neurons encode the positions of different objects in the scene.
Inferior temporal cortex (IT) neurons have reduced receptive field sizes in complex natural scenes. This facilitates the read-out of information about individual objects from IT, but raises the question of whether more than the single object present at the fovea is represented by the firing of IT neurons, as would be important for whole scene perception in which several objects may be located w...
متن کاملRobust Method for E-Maximization and Hierarchical Clustering of Image Classification
We developed a new semi-supervised EM-like algorithm that is given the set of objects present in eachtraining image, but does not know which regions correspond to which objects. We have tested thealgorithm on a dataset of 860 hand-labeled color images using only color and texture features, and theresults show that our EM variant is able to break the symmetry in the initial solution. We compared...
متن کاملTechniques for Still Image Scene Classification and Object Detection
In this paper we consider the interaction between different semantic levels in still image scene classification and object detection problems. We present a method where a neural method is used to produce a tentative higher-level semantic scene representation from low-level statistical visual features in a bottom-up fashion. This emergent representation is then used to refine the lower-level obj...
متن کاملFormal system based on fuzzy logic applied to digital image scene analysis
In this paper, a new approach of the digital image scene analysis is presented. In order to provide a flexible theoretical background for digital image data acquisition, image object recombinig and image scene analysis a formal system is introduced. In order to implement a formal system in a context of digital image analysis, a formal language is also introduced. Basic idea behind it is that si...
متن کامل