Deep Multilabel CNN for Forensic Footwear Impression Descriptor Identification

TL;DR

This paper introduces a deep learning method for classifying forensic footwear impression features, utilizing a learnable preprocessing layer and multiple interpolation techniques to improve accuracy and efficiency in transfer learning scenarios.

Contribution

The paper proposes a novel approach combining learnable preprocessing and multiple interpolation methods for improved footwear impression classification using transfer learning.

Findings

Learnable preprocessing with multiple interpolation outperforms single interpolation.

Preserving aspect ratio significantly boosts accuracy.

Efficient use of low-resolution inputs reduces computational costs.

Abstract

In recent years deep neural networks have become the workhorse of computer vision. In this paper, we employ a deep learning approach to classify footwear impression's features known as \emph{descriptors} for forensic use cases. Within this process, we develop and evaluate an effective technique for feeding downsampled greyscale impressions to a neural network pre-trained on data from a different domain. Our approach relies on learnable preprocessing layer paired with multiple interpolation methods used in parallel. We empirically show that this technique outperforms using a single type of interpolated image without learnable preprocessing, and can help to avoid the computational penalty related to using high resolution inputs, by making more efficient use of the low resolution inputs. We also investigate the effect of preserving the aspect ratio of the inputs, which leads to considerable boost in accuracy without increasing the computational budget with respect to squished rectangular images. Finally, we formulate a set of best practices for transfer learning with greyscale inputs, potentially widely applicable in computer vision tasks ranging from footwear impression classification to medical imaging.