Blind Users Accessing Their Training Images in Teachable Object Recognizers

TL;DR

This paper presents MyCam, a mobile app that enables blind users to iteratively train object recognizers by providing non-visual descriptors, improving accessibility of training and evaluation processes.

Contribution

It introduces a novel approach with real-time photo descriptors for blind users, enhancing accessibility in training object recognizers.

Findings

Blind users reduced cropped object photos using descriptors

Participants could add more variations through iteration

Users found the app simple and useful

Abstract

Iteration of training and evaluating a machine learning model is an important process to improve its performance. However, while teachable interfaces enable blind users to train and test an object recognizer with photos taken in their distinctive environment, accessibility of training iteration and evaluation steps has received little attention. Iteration assumes visual inspection of the training photos, which is inaccessible for blind users. We explore this challenge through MyCam, a mobile app that incorporates automatically estimated descriptors for non-visual access to the photos in the users' training sets. We explore how blind participants (N=12) interact with MyCam and the descriptors through an evaluation study in their homes. We demonstrate that the real-time photo-level descriptors enabled blind users to reduce photos with cropped objects, and that participants could add more variations by iterating through and accessing the quality of their training sets. Also, Participants found the app simple to use indicating that they could effectively train it and that the descriptors were useful. However, subjective responses were not reflected in the performance of their models, partially due to little variation in training and cluttered backgrounds.