To quantitatively evaluate our model we must first produce a dataset of “scene”-like images: images with occlusion and spatially varying illumination. We will do this by layering the objects in the MIT intrinsic images dataset [4] (using the ground-truth shapes produced by Berkeley [2]) into a scene, and then rendering the resulting shapes using a randomly sampled spatially-varying illumination...

A central research question in natural vision is how to allocate fixation to extract informative cues for scene perception. With high quality images, psychological and computational studies have made significant progress to understand and predict human gaze allocation in scene exploration. However, it is unclear whether these findings can be generalised to degraded naturalistic visual inputs. I...

In this paper we study the statistical properties of natural images belonging to different categories and their relevance for scene and object categorization tasks. We discuss how second-order statistics are correlated with image categories, scene scale and objects. We propose how scene categorization could be computed in a feedforward manner in order to provide top-down and contextual informat...

Centre-surround interaction in the primary visual cortex (area V1) has been studied extensively using artificial, abstract stimulus patterns, such as bars, gratings and simple texture patterns. In this experiment, we extend the study of centre-surround interaction by using natural scene images. We systematically varied the contrast of natural image surrounds presented outside the classical rece...

Passive eye-pose estimation methods that recover the eye-pose from natural images generally suffer from low accuracy, the result of a static eye model, and the recovery of the eye model from the estimated iris contour. Active eye-pose estimation methods use precisely calibrated light sources to estimate a user specific eye-model. These methods recover an accurate eye-pose at the cost of complex...

The objective of this study is to propose a new method for text region localization and character extraction in natural scene images with complex background. In this paper, a hybrid methodology is suggested which extracts multilingual text from natural scene image with cluttered backgrounds. The proposed approach involves four steps. First, potential text regions in an image are extracted based...

The direction in which people tend to move their eyes when inspecting images can reveal the different influences on eye guidance in scene perception, and their time course. We investigated biases in saccade direction during a memory-encoding task with natural scenes and computer-generated fractals. Images were rotated to disentangle egocentric and image-based guidance. Saccades in fractals were...

Retrieval of text information from natural scene images and video frames is a challenging task due to its inherent problems like complex character shapes, low resolution, background noise, etc. Available OCR systems often fail to retrieve such information in scene/video frames. Keyword spotting, an alternative way to retrieve information, performs efficient text searching in such scenarios. How...

A PC system for recognition of natural scene images including human faces and various objects is proposed. Coarse region segmentation of real images with 64×64 pixels at the video rate is achieved by using the FPGA implementation of resistive-fuse networks. A flexible template matching based on dynamic-link architecture is performed on our PC system.

Conceptual graphs are very useful for representing structured knowledge. However, existing formulations of fuzzy conceptual graphs are not suitable for matching images of natural scenes. This paper presents a new variation of fuzzy conceptual graphs that is more suited to image matching. This variant differentiates between a model graph that describes a known scene and an image graph which desc...