A New Automatic Method to Adjust Parameters for Object Recognition

TL;DR

This paper introduces an automated parameter adjustment method for object recognition using reinforcement learning, involving user and parameter agents to improve recognition accuracy without manual tuning.

Contribution

It presents a novel reinforcement learning-based approach that automates parameter tuning in object recognition, incorporating user preferences for improved adaptability.

Findings

Automates parameter adjustment process for object recognition.

Uses reinforcement learning with user and parameter agents.

Reduces manual effort in parameter tuning.

Abstract

To recognize an object in an image, the user must apply a combination of operators, where each operator has a set of parameters. These parameters must be well adjusted in order to reach good results. Usually, this adjustment is made manually by the user. In this paper we propose a new method to automate the process of parameter adjustment for an object recognition task. Our method is based on reinforcement learning, we use two types of agents: User Agent that gives the necessary information and Parameter Agent that adjusts the parameters of each operator. Due to the nature of reinforcement learning the results do not depend only on the system characteristics but also on the user favorite choices.