An object localization optimization technique in medical images using plant growth simulation algorithm

Abstract

The analysis of leukocyte images has drawn interest from fields of both medicine and computer vision for quite some time where different techniques have been applied to automate the process of manual analysis and classification of such images. Manual analysis of blood samples to identify leukocytes is time-consuming and susceptible to error due to the different morphological features of the cells. In this article, the nature-inspired plant growth simulation algorithm has been applied to optimize the image processing technique of object localization of medical images of leukocytes. This paper presents a random bionic algorithm for the automated detection of white blood cells embedded in cluttered smear and stained images of blood samples that uses a fitness function that matches the resemblances of the generated candidate solution to an actual leukocyte. The set of candidate solutions evolves via successive iterations as the proposed algorithm proceeds, guaranteeing their fit with the actual leukocytes outlined in the edge map of the image. The higher precision and sensitivity of the proposed scheme from the existing methods is validated with the experimental results of blood cell images. The proposed method reduces the feasible sets of growth points in each iteration, thereby reducing the required run time of load flow, objective function evaluation, thus reaching the goal state in minimum time and within the desired constraints.

Gaussian Processes with Context-Supported Priors for Active Object Localization

“…Anthony D. Rhodes 1 , Jordan Witte 2 , Melanie Mitchell 2,3 , Bruno Jedynak 1 Portland State University: 1 Department of Mathematics and Statistics, 2 Computer Science; 3 Santa Fe Institute as an active search integrating top-down information in concert with a dynamic Bayesian optimization procedure requiring very few bounding-box proposals for high accuracy. (3) By rendering an active Bayesian search, our method can provide a principled and interpretable groundwork for more complex vision tasks, which we show explicitly through the incorporation of flexible context models.…”

“…Our work provides the following contributions: (1) We demonstrate that CNN features computed from an objectproposal bounding box can be used to predict spatial offset from a target object. (2) We frame the localization process as an active search integrating top-down information in concert with a dynamic Bayesian optimization procedure requiring very few bounding-box proposals for high accuracy.…”

“…Our work provides the following contributions: (1) We demonstrate that CNN features computed from an objectproposal bounding box can be used to predict spatial offset from a target object. (2) We frame the localization process…”

Bayesian optimization for refining object proposals

“…More proposals for fine-grained localization is a vital task for many real-world applications of computer vision, including autonomous driving [7], object tracking, medical computer vision [1], and robotics [15]. In this paper, we describe an algorithm that improves in several ways on the boundingbox regression method used in R-CNN and other state-ofthe-art object-detection architectures.…”