J
Jack Greenhalgh
Researcher at University of Bristol
Publications - 12
Citations - 663
Jack Greenhalgh is an academic researcher from University of Bristol. The author has contributed to research in topics: Maximally stable extremal regions & Optical character recognition. The author has an hindex of 7, co-authored 10 publications receiving 516 citations. Previous affiliations of Jack Greenhalgh include University College London.
Papers
More filters
Journal ArticleDOI
Real-Time Detection and Recognition of Road Traffic Signs
Jack Greenhalgh,Majid Mirmehdi +1 more
TL;DR: The proposed system is accurate at high vehicle speeds, operates under a range of weather conditions, runs at an average speed of 20 frames per second, and recognizes all classes of ideogram-based (nontext) traffic symbols from an online road sign database.
Journal ArticleDOI
Recognizing Text-Based Traffic Signs
Jack Greenhalgh,Majid Mirmehdi +1 more
TL;DR: A novel system for the automatic detection and recognition of text in traffic signs using Maximally stable extremal regions and hue, saturation, and value color thresholding to locate a large number of candidates and interprets the text contained within detected candidate regions.
Journal ArticleDOI
Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions
Michael Phillips,Michael Phillips,Helen Marsden,Wayne Jaffe,Rubeta N Matin,G.N. Wali,Jack Greenhalgh,Emily McGrath,Rob James,Evmorfia Ladoyanni,Anthony Bewley,Giuseppe Argenziano,Ioulios Palamaras +12 more
TL;DR: As the burden of skin cancer increases, artificial intelligence technology could play a role in identifying lesions with a high likelihood of melanoma.
Proceedings Article
Traffic sign recognition using MSER and Random Forests
Jack Greenhalgh,Majid Mirmehdi +1 more
TL;DR: A novel system for the real-time detection and recognition of traffic symbols that can operate under a range of weather conditions at an average speed of 20 fps and is accurate even at high vehicle speeds is presented.
Journal ArticleDOI
Detection of Malignant Melanoma Using Artificial Intelligence: An Observational Study of Diagnostic Accuracy
TL;DR: Deep Ensemble for Recognition of Melanoma has the potential to be used as a decision support tool in primary care, by providing dermatologist-grade recommendation on the likelihood of malignant melanoma.