Tiffany Song
Human-Computer Interaction Design, Indiana University Bloomington, Bloomington, IN, USA

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Computer-Vision-Informed Visual Explanation Cards for Autonomous-Driving Traffic-Sign Alerts: Localization, Classification, and Retrieved Evidence on GTSDB Ruiyan Ma; Long Zhang; Tiffany Song
International Journal of Graphic Design Vol. 3 No. 2 (2025): October| IJGD: International Journal of Graphic Design
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/ijgd.v3i2.3991

Abstract

This paper develops a computer-vision-informed visual explanation card for traffic-sign alerts in autonomous-driving and driver-assistance interfaces. The card organizes a detected sign crop, predicted class, confidence, default semantic display-priority tier, retrieved visual precedents, scene-location cue, and concise action prompt. The empirical study uses the complete German Traffic Sign Detection Benchmark (GTSDB), comprising 900 road scenes in the standard 600-scene development and 300-scene evaluation portions. The same scenes support localization, crop classification, retrieval, calibration, and end-to-end analysis. The first 600 scenes were divided at the scene level into training and validation subsets; the 300 evaluation scenes were held out until model choices, retrieval depth, fusion weight, and detector threshold had been fixed. A learned class-agnostic localizer filters color-connected-component proposals with a histogram-of-oriented-gradients and color classifier. Five crop classifiers and four nearest-neighbor settings were evaluated, with retrieval treated primarily as example-based explanation support. On the held-out scenes, the selected localizer achieved an AP at IoU 0.50 of 0.211, an AP averaged over IoU 0.50–0.95 of 0.098, and a recall of 0.260 at the validation-selected operating point. The selected crop classifier achieved 0.784 accuracy and 0.574 macro-F1 on ground-truth crops. With predicted crops, correct-class end-to-end coverage was 0.177, and correct-tier end-to-end coverage was 0.244. These results define the information that the proposed card can receive from the evaluated vision pipeline. They do not measure driver comprehension, glance behavior, response time, trust, usability, or deployment safety, which require separate human-centred evaluation.
Innovation Capability Gap in Design Practice: Uncovering Organizational Constraints Yuli Fitrianto; Ahmad Zainudin; Tiffany Song; Reza Prabowo
International Journal of Graphic Design Vol. 4 No. 2 (2026): October| IJGD: International Journal of Graphic Design
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/ijgd.v4i2.3646

Abstract

The potential of design professionals to drive innovation is often constrained by organizational environments, creating a gap between embedded innovation capability and its practical activation. This study develops a conceptual model to explore how organizational constraints may affect the activation of innovation capability and its translation into innovation outcomes within design practice. A descriptive conceptual approach was employed, integrating a critical analytical essay, a comparative analysis of idealized versus constraint-driven design practice, and an illustrative case simulation using hypothetical profiles and dummy data. The simulation was designed to illustrate the model's underlying logic under specified assumptions rather than to measure actual organizational conditions or establish empirical relationships. The conceptual analysis suggests that structural rigidities, risk-averse cultural norms, and centralized decision-making may constrain the translation of design capability into innovation outcomes. The illustrative simulation demonstrates how these assumed constraints could influence innovation-related processes within the proposed framework; however, the simulated patterns should not be interpreted as evidence of actual organizational behavior. This study reframes innovation discourse from an individual-centric to a system-centric perspective by introducing an activation-based view, which conceptually distinguishes the availability of individual capability from the organizational conditions that may enable or restrict its application. The proposed framework offers a conceptual diagnostic lens for examining potential barriers to innovation in design practice, including creative studio workflows, visual communication development, design revision processes, and approval procedures. It provides a basis for further empirical investigation into how organizational conditions may shape the relationship between design capability and innovation outcomes.