Genetic tuning of a laser pointer environment control device system for handicapped people with fuzzy systems

Automatic Laser Pointer Detection Algorithm for Environment Control Device Systems Based on Template Matching and Genetic Tuning of Fuzzy Rule-Based Systems

“…For this reason, in 16 we presented a new approach hybridizing a classic technique with the use of a Fuzzy Rule-Based System (FRBS) designed using expert knowledge 3 , 45 , 46 to try to improve the success rate in images without laser spots. Further, this initial FRBS was tuned in 15 by means of a Genetic Algorithm (GA), in order to improve the success rate in images without laser spots.…”

“…In this paper, we present a new approach to detect the laser spot in the environment device control system presented in 15 and 16 by considering the color influence in laser spot detection and using a simple automatic Rule Base (RB) generation. This method solves the problems that the approaches proposed in 15 and 16 present when dealing with new situations as a consequence of extending the set of available example images from 105 in 15 , 16 to 990.…”

“…This method solves the problems that the approaches proposed in 15 and 16 present when dealing with new situations as a consequence of extending the set of available example images from 105 in 15 , 16 to 990. This new set of example images represents an almost complete range of different light and distance conditions in their real use by humans, and it allows us to consider a cross fold validation approach in order to adequately validate the proposed approaches.…”

“…Since it involves a significant increase in the number of variables and the generation of a new set of rules for the FRBS, we apply a simple automatic rule generation method 58 , 59 considering the extended set of images and following a cross validation approach instead of trying an expert based generation as in 15 and then in 16 . With this new approach, we analyze the morphology and the color of the laser spot images, making it more precise than the previous approaches.…”

Hardware Implementation and Validation of 3D Underwater Shape Reconstruction Algorithm Using a Stereo-Catadioptric System

“…In [17], authors present an approach that permits to differentiate good and bad detections by analyzing the proportionality between the projection surface diameter and the number of classified laser pixels in a group. In [18], fuzzy rule based system adjusted by a genetic algorithm is proposed to improve the success rate of the laser pointer detection algorithm decreasing as much as possible the false-offs. In [19], authors developed an approach based on motion estimation to extract "good" features.…”