J
John M. Trenkle
Researcher at Environmental Research Institute of Michigan
Publications - 14
Citations - 2094
John M. Trenkle is an academic researcher from Environmental Research Institute of Michigan. The author has contributed to research in topics: Feature (machine learning) & Feature extraction. The author has an hindex of 8, co-authored 14 publications receiving 2012 citations.
Papers
More filters
N-gram-based text categorization
W.B. Cavnar,John M. Trenkle +1 more
TL;DR: An N-gram-based approach to text categorization that is tolerant of textual errors is described, which worked very well for language classification and worked reasonably well for classifying articles from a number of different computer-oriented newsgroups according to subject.
Journal ArticleDOI
Microarrays of tumor cell derived proteins uncover a distinct pattern of prostate cancer serum immunoreactivity.
Kerri Bouwman,Ji Qiu,Heping Zhou,Mark Schotanus,Leslie A. Mangold,Robert C. Vogt,Erik Erlandson,John M. Trenkle,Alan W. Partin,David E. Misek,Gilbert S. Omenn,Brian B. Haab,Samir M. Hanash +12 more
TL;DR: The use of microarrays of tumor‐derived proteins to profile the antibody repertoire in the sera of prostate cancer patients and controls suggests that microarray of fractionated proteins could be a powerful tool for tumor antigen discovery and cancer diagnosis.
PatentDOI
Mosaic construction, processing, and review of very large electronic micrograph composites
Robert C. Vogt,John M. Trenkle +1 more
TL;DR: In this paper, a method for acquisition, mosaicking, cueing and interactive review of large-scale transmission electron micrograph composite images is described, where individual frames are automatically registered and mosaiced together into a single virtual image composite, which is then used to perform automatic cueing of axons and axon clusters.
Arabic Text Recognition System
TL;DR: A system for the recognition of Arabic text in document images that is designed to perform well on low resolution and low quality document images.
Proceedings ArticleDOI
Word-level recognition of multifont Arabic text using a feature vector matching approach
TL;DR: A word-level recognition system for machine-printed Arabic text has been implemented and has obtained promising word recognition rates on low-quality multifont text imagery.