Optical pattern recognition

Recent research in visual object recognition has shown that context can facilitate object recognition. This study assessed the effect of self-relevant familiarity of context in object recognition. Participants performed a task in which they had to recognize degraded objects shown under varying levels of contextual information. The level of degradation at which they could successfully recognize the target object was used as a measure of performance. There were five contextual conditions: (1) no context, (2) context, (3) context and size, (4) context and location, (5) context, size and location. Within each contextual condition, we compared the performance of "Expert" participants who viewed objects in the context of their own house and "Novice" participants who viewed those particular settings for the first time. Ratings were performed to assess each object's consistency, frequency, position consistency, typicality and shape distinctiveness. Object's size was the only contextual info rmation that did not affect performance. Contextual information significantly reduced the amount of bottom-up visual information needed for object identification for both experts and novices. An interaction (Contextual Information x Level of Familiarity) was observed. Expert participants' performance improved significantly more than novice participants' performance by the presence of contextual information. Location information affected the performance of expert participants, only when objects that occupied stable positions were considered. Both expert and novice participants performed better with objects that rated high in typicality and shape distinctiveness. Object's consistency, frequency and position consistency did not seem to affect expert participants' performance but did affect novice participants' performance.

Contemporary computer vision solutions to the problem of object detection aim at incorporating contextual information into the process. This thesis proposes a systematic evaluation of the usefulness of incorporating knowledge about the geometric context of a scene into a baseline object detection algorithm based on local features. This research extends publicly available MATLABRª implementations of leading algorithms in the field and integrates them in a coherent and extensible way. Experiments are presented to compare the performance and accuracy between baseline and context-based detectors, using images from the recently published SUN09 dataset. Experimental results demonstrate that adding contextual information about the geometry of the scene improves the detector performance over the baseline case in 50% of the tested cases.

Biometrics is the science and technology of measuring and analyzing biological data for authentication purposes. Its progress has brought in a large number of civilian and government applications. The candidate modalities used in biometrics include retinas, fingerprints, signatures, audio, faces, etc. There are two types of biometric system: single modal systems and multiple modal systems. Single modal systems perform person recognition based on a single biometric modality and are affected by problems like noisy sensor data, intra-class variations, distinctiveness and non-universality. Applying multiple modal systems that consolidate evidence from multiple biometric modalities can alleviate those problems of single modal ones. Integration of evidence obtained from multiple cues, also known as fusion, is a critical part in multiple modal systems, and it may be consolidated at several levels like feature fusion level, matching score fusion level and decision fusion level. Among biometric modalities, both audio and face modalities are easy to use and generally acceptable by users. Furthermore, the increasing availability and the low cost of audio and visual instruments make it feasible to apply such Audio-Visual (AV) systems for security applications. Therefore, this dissertation proposes an algorithm of face recognition. In addition, it has developed some novel algorithms of fusion in different levels for multiple modal biometrics, which have been tested by a virtual database and proved to be more reliable and robust than systems that rely on a single modality.