Classification and visualization based on derived image features: application to genetic syndromes

PLoS One. 2014 Nov 18;9(11):e109033. doi: 10.1371/journal.pone.0109033. eCollection 2014.

Abstract

Data transformations prior to analysis may be beneficial in classification tasks. In this article we investigate a set of such transformations on 2D graph-data derived from facial images and their effect on classification accuracy in a high-dimensional setting. These transformations are low-variance in the sense that each involves only a fixed small number of input features. We show that classification accuracy can be improved when penalized regression techniques are employed, as compared to a principal component analysis (PCA) pre-processing step. In our data example classification accuracy improves from 47% to 62% when switching from PCA to penalized regression. A second goal is to visualize the resulting classifiers. We develop importance plots highlighting the influence of coordinates in the original 2D space. Features used for classification are mapped to coordinates in the original images and combined into an importance measure for each pixel. These plots assist in assessing plausibility of classifiers, interpretation of classifiers, and determination of the relative importance of different features.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Biometric Identification / methods*
  • Craniofacial Abnormalities / classification*
  • Humans
  • Image Processing, Computer-Assisted / methods*

Grants and funding

This work was supported by DFG grants BO 1955/2-3 and WU 314/6-2, and by two grants (CRANIRARE and FACE) from the German Ministry of Research and Education to D.W. (BMBF 01GM0802). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.