Detecting Repeating Objects using Patch Correlation Analysis
This work addresses the need for efficient object detection in images with minimal user input, offering a practical solution for applications like image analysis, though it is incremental in improving existing methods.
The paper tackles the problem of detecting and counting repeating objects in images without requiring user-annotated training data, achieving higher accuracy than state-of-the-art techniques through an unsupervised method that uses patch correlation analysis and active learning.
In this paper we describe a new method for detecting and counting a repeating object in an image. While the method relies on a fairly sophisticated deformable part model, unlike existing techniques it estimates the model parameters in an unsupervised fashion thus alleviating the need for a user-annotated training data and avoiding the associated specificity. This automatic fitting process is carried out by exploiting the recurrence of small image patches associated with the repeating object and analyzing their spatial correlation. The analysis allows us to reject outlier patches, recover the visual and shape parameters of the part model, and detect the object instances efficiently. In order to achieve a practical system which is able to cope with diverse images, we describe a simple and intuitive active-learning procedure that updates the object classification by querying the user on very few carefully chosen marginal classifications. Evaluation of the new method against the state-of-the-art techniques demonstrates its ability to achieve higher accuracy through a better user experience.