Deep Multilabel CNN for Forensic Footwear Impression Descriptor Identification
This work provides an incremental improvement in footwear impression classification for forensic analysts by proposing a more efficient and accurate method for processing low-resolution grayscale inputs.
This paper addresses the problem of classifying footwear impression descriptors for forensic use cases using deep neural networks. The authors developed a technique involving a learnable preprocessing layer paired with multiple interpolation methods for downsampled grayscale impressions, which empirically outperformed single interpolation methods without learnable preprocessing. They also found that preserving the aspect ratio of inputs significantly boosted accuracy without increasing computational cost.
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.