Abstract

ABSTRACT Transformation invariant image recognition has been an active research area due to its widespread applications in a variety of fields such as military operations, robotics, medical practices, geographic scene analysis, and many others. The primary goal for this research is detection of objects in the presence of image transf ormations such as changes in resolution, rotation, translation, scale and occlusion. We investigate a biologically-inspired neural network (NN) model for such transformation-invariant object recognition. In a classical training-testing setup for NN, the performance is largely dependent on the range of transformation or orientation involved in training. However, an even more serious dilemma is that there may not be enough trai ning data available for succes sful learning or even no training data at all. To alleviate this problem, a biologically inspired reinforcement learning (RL) approach is proposed. In this paper, the RL approach is explored for object recognition with different types of transformations such as changes in scale, size, resolution and rotation. The RL is implemented in an ad aptive critic design (ACD) framew ork, which approximates the neuro-dynamic programming of an action network and a critic network, respectively. Two ACD algorithms such as Heuristic Dynamic Programming (HDP) and Dual Heuristic dynamic Programming (DHP) are investigated to obtain transformation invariant object recognition. The two learning algorithms are evaluated statistically using simulated transformations in images as well as w ith a large-scale UMIST face database with pose variations. In the face database authentication case, the 90 q out-of-plane rotation of faces from 20 different subjects in the UMIST database is used. Our simulations show promising results for both designs for transformation-invariant object recognition and authentication of faces. Comparing the two algorithms, DHP outperforms HDP in learning capability, as DHP takes fewer steps to perform a successful recognition task in gene ral. Further, the residual critic error in DHP is generally smaller than that of HDP, and DHP achieves a 100% success rate more frequently than HDP for individual obj ects/subjects. On the other hand, HDP is more robust than the DHP as far as success rate across the database is concerned when applied in a stochastic and uncertain environment, and the computational time involved in DHP is more. Keywords: Reinforcement Learning (RL), automatic object recognition (AOR), Heuristic Dynamic Programming (HDP), Dual Heuristic dynamic Programming (DHP), image transformation

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call