← Computer Vision vault · references · CV1–CV7

Computer Vision — references & extra reads.

computer-vision references AIMLCZG525

The textbooks, courses and papers behind the AIMLCZG525 Computer Vision mid-sem material — image formation, digital image fundamentals, low-level processing, edges, Canny, Hough, Harris corners, HoG and SIFT. Start with Szeliski for broad vision context and Gonzalez & Woods / Sonka for image-processing depth.

Textbooks

  • T1Richard Szeliski — Computer Vision: Algorithms and Applications, 2nd ed. Broad, modern, free online textbook covering image formation, features, matching, segmentation, recognition, reconstruction and applications. szeliski.org/Book
  • T2Milan Sonka, Vaclav Hlavac & Roger Boyle — Image Processing, Analysis, and Machine Vision, 4th ed., Cengage Learning. Course-listed textbook for image analysis foundations: digitization, filtering, edges, regions, shape and machine vision systems.
  • T3Rafael C. Gonzalez & Richard E. Woods — Digital Image Processing. Best reference for histograms, intensity transforms, spatial filtering, smoothing, sharpening, Canny and Hough-style classical image processing.
  • T4Valliappa Lakshmanan, Martin Görner & Ryan Gillard — Practical Machine Learning for Computer Vision, O'Reilly, 2021. Applied ML reference for end-to-end image pipelines, datasets, model training, deployment and production trade-offs.

Courses & lecture resources

  • C1Stanford CS231n — Convolutional Neural Networks for Visual Recognition. Excellent modern companion for image classification, recognition and deep-learning parts of computer vision. Notes are free online. cs231n.github.io
  • C2Cornell Tech — Intro to Computer Vision, Noah Snavely. Source lineage for several lecture slides: why vision is hard, image formation, local features, matching, geometry and classical/modern vision framing. cs.cornell.edu/courses/cs5670
  • C3First Principles of Computer Vision — Shree Nayar. Clear visual explanations of filtering, gradients, features, cameras and geometry; especially helpful for box filters, Gaussian filters, Hough intuition and SIFT-style feature thinking. fpcv.cs.columbia.edu
  • C4BITS Pilani WILP — Computer Vision (AIMLCZG525). Course lecture decks CV1–CV7: introduction, digital image fundamentals, low-level vision, edge/line detection, Canny, Hough, Harris, HoG and SIFT.

Papers

TopicReferenceWhy it matters
CannyJohn Canny (1986) — "A Computational Approach to Edge Detection." IEEE Transactions on Pattern Analysis and Machine Intelligence. doi.org/10.1109/TPAMI.1986.4767851Defines the famous edge detector around good detection, good localization and single response.
HarrisChris Harris & Mike Stephens (1988) — "A Combined Corner and Edge Detector." Alvey Vision Conference. doi.org/10.5244/C.2.23Introduces the structure-tensor response used for corner detection and image matching.
SIFTDavid G. Lowe (2004) — "Distinctive Image Features from Scale-Invariant Keypoints." International Journal of Computer Vision. cs.ubc.ca/~lowe/papers/ijcv04.pdfCanonical local-feature pipeline: scale-space extrema, orientation assignment, 128-D descriptor and robust matching.
HoGNavneet Dalal & Bill Triggs (2005) — "Histograms of Oriented Gradients for Human Detection." CVPR. lear.inrialpes.fr/people/triggs/pubs/Dalal-cvpr05.pdfDefines the classic HoG descriptor and pedestrian-detection pipeline.
Shi-TomasiJianbo Shi & Carlo Tomasi (1994) — "Good Features to Track." CVPR. ai.mit.edu/courses/6.891/handouts/shi94good.pdfRefines corner quality with the minimum eigenvalue criterion for stable tracking.

Extra reads

  • E1OpenCV documentation. Practical API reference for histogram equalization, filtering, Canny, Hough lines/circles, Harris corners, HoG and SIFT. docs.opencv.org
  • E2scikit-image documentation. Python-friendly examples for image transforms, filters, feature detectors and classical CV algorithms. scikit-image.org/docs/stable
  • E3Chromatone color models. Interactive color-space explanations referenced by the lecture deck for RGB/HSV/CMYK intuition. chromatone.center/theory/color/models
  • E4Computer Vision vault companions. Use the cheatsheet for compact revision and the formula sheet for exam equations.
← Computer Vision vault
© cvam — written in plaintext, served warm