{"id":10629,"date":"2020-02-24T10:52:28","date_gmt":"2020-02-24T10:52:28","guid":{"rendered":"http:\/\/blog.bachi.net\/?p=10629"},"modified":"2020-06-29T14:45:36","modified_gmt":"2020-06-29T14:45:36","slug":"tsm_compvis","status":"publish","type":"post","link":"https:\/\/blog.bachi.net\/?p=10629","title":{"rendered":"TSM_CompVis"},"content":{"rendered":"

Neural Networks and Deep Learning<\/a>
\nDeep Learning<\/a>, Ian Goodfellow and Yoshua Bengio and Aaron Courville
\nCode samples for my book “Neural Networks and Deep Learning”<\/a>
\nCS231n Convolutional Neural Networks for Visual Recognition<\/a>
\nPadding and Stride<\/a>
\nA Beginner’s Guide To Understanding Convolutional Neural Networks Part 2<\/a><\/p>\n

<\/p>\n

skimage<\/h2>\n

General examples<\/a>
\nHysteresis thresholding<\/a>
\nMean filters<\/a>
\nDenoising a picture<\/a>
\nUnsharp masking<\/a>
\nCanny edge detector<\/a>
\nStraight line Hough transform<\/a>
\nCircular and Elliptical Hough Transforms<\/a>
\nRescale, resize, and downscale<\/a>
\nPiecewise Affine Transformation<\/a>
\nHistogram Equalization<\/a>
\nRGB to grayscale<\/a>
\nAdapting gray-scale filters to RGB images<\/a>
\nThresholding<\/a>, Otsu’s method
\nMorphological Filtering<\/a>
\nRank filters<\/a>
\nImage Segmentation<\/a>
\nA crash course on NumPy for images<\/a><\/p>\n

API<\/h4>\n

Module: io<\/a>
\nModule: filters<\/a>
\nModule: transform<\/a>
\nModule: morphology<\/a>
\nModule: color<\/a>
\nModule: exposure<\/a><\/p>\n

Tutorial<\/h4>\n

Bright ridge detection not working as expected with Frangi<\/a>, Frangi-, Hessian-Filter
\nIPython (Jupyter) widgets: An image convolution demo<\/a>
\nWiener Filter for image deblur<\/a>
\ngithub.com\/scikit-image\/skimage-demos\/blob\/master\/clock_deblur.py<\/a>
\nHistogram Equalization<\/a><\/p>\n

<\/p>\n

scipy<\/h2>\n

Multidimensional image processing (scipy.ndimage)<\/a><\/p>\n

API<\/h4>\n

scipy.ndimage.binary_fill_holes<\/a><\/p>\n

<\/p>\n

Python<\/h2>\n

python-kurs.eu<\/h4>\n

Generatoren und Iteratoren<\/a>
\nLambda, filter, reduce und map<\/a>
\nListen-Abstraktion (List Comprehension)<\/a><\/p>\n

ORDIX blog<\/h4>\n

Python Generator-Funktionen und -Expressions: Ein alter Hut kann auch modern sein<\/a>
\nEinstieg in Neuronale Netze mit TensorFlow und Keras<\/a>
\nData Mining in der Praxis (Teil I): Was ist Data Mining?<\/a>
\nData Mining in der Praxis (Teil II): Klassifikation<\/a>
\nData Mining in der Praxis (Teil III) Lineare Regression<\/a><\/p>\n

Real Python<\/h4>\n

Python 3’s f-Strings: An Improved String Formatting Syntax (Guide)<\/a><\/p>\n

\r\nname = "Eric"\r\nage = 28\r\n\r\n### Option #1: %-formatting\r\nprint("Hello, %s. You are %d." % (name, age))\r\n\r\n### Option #2: str.format()\r\nprint("Hello, {}. You are {}.".format(name, age))\r\n\r\n### Option #3: f-Strings\r\nprint(f"Hello, {name}. You are {age}.")\r\n<\/pre>\n
<\/p>\n
Homework<\/h2>\n
Digitize your Receipts using Computer Vision<\/a>
\nDeep Dive Into OCR for Receipt Recognition<\/a>
\nSimple OCR implementation on Android with Google\u2019s ML Kit<\/a><\/p>\n
find intersection point of two lines drawn using houghlines opencv<\/a>
\nIntersection of two lines defined in (rho\/theta ) parameterization<\/a>
\nReading multiple invoices from an image using OCR\/computer vision<\/a>
\nHow can I detect an object from static image and crop it from the image using openCV?<\/a>
\nReceipt Scanning – How to scan a receipt and extract data from it<\/a><\/p>\n
how to find coordinates of intersection of lines after using “houghlines”<\/a><\/p>\n
Expense Reports in a Snap (or a Tap)<\/a><\/p>\n
Homogene Koordinaten<\/h4>\n
Homogene Koordinaten<\/a>
\nEbenengleichung<\/a>
\nKoordinatenform<\/a><\/p>\n
Homogene Koordinaten<\/a>
\nLecture 2: Homogeneous Coordinates, Lines and Conics<\/a> (PDF)<\/p>\n
<\/p>\n
Computer Vision (SBE404B)<\/h4>\n
Asem Alaa<\/a>
\nEslamAdel<\/a>
\nAyman Anwar<\/a><\/p>\n
Computer Vision (SBE404B) – Spring 2020<\/a>
\nComputer Vision (SBE404B) – Spring 2019<\/a>
\nComputer Vision (SBE404B) – Spring 2018<\/a><\/p>\n
Week 1: Warming up with Python Basics<\/a>
\nWeek 2: Image Processing 1<\/a>
\nWeek 3: Images in Frequency Domain<\/a>
\nWeek 4: Image Filtering and Edge Detection<\/a>
\nWeek 5: Hough Transform (Line and Circle Detection)<\/a>
\nWeek 6: Corner Detection<\/a>
\nWeek 7: Segmentation (Thresholding and Region growing)<\/a>
\nWeek 8: Segmentation (Clustering Segmentation)<\/a>
\nWeek 10: Image features, feature descriptors, and feature matching<\/a><\/p>\n
github.com\/sbme-tutorials\/cv-week1-demo<\/a>
\ngithub.com\/sbme-tutorials\/sbe401-week2-demo<\/a>
\ngithub.com\/sbme-tutorials\/cv_week3_demo<\/a>
\ngithub.com\/sbme-tutorials\/cv-week4-demo<\/a>
\ngithub.com\/sbme-tutorials\/cv-week8-demo<\/a><\/p>\n
<\/p>\n
Week 1<\/h2>\n
Deep Learning Alchemy to close the Perception Loop in Vision: Part 1 – Image Alignment with Pytorch<\/a>
\nCS231n Convolutional Neural Networks for Visual Recognition – Python Numpy Tutorial<\/a>
\nCS228 Python Tutorial<\/a> (Notebook)
\nPython Single Line For Loops<\/a>
\nThe Confusing Double Colon (::) in NumPy<\/a><\/p>\n
Flags<\/h3>\n
PyX \u2014 Python graphics package<\/a>
\nPython:Flags Tutorial<\/a>
\nPython:Flags with Lines Tutorial<\/a><\/p>\n
Python Essentials<\/h3>\n
Data Structure<\/h4>\n
4. Data Structures (list, dict, tuples, sets, strings)<\/a>
\n5. Data Structures<\/a><\/p>\n
Python Data Types<\/a>
\nBasic Data Types in Python<\/a>
\nPython Data Types<\/a>
\nData Types in Python<\/a><\/p>\n
Format String<\/h4>\n
Format String Syntax<\/a>
\nFormat String Syntax<\/a>
\nFormat Specification Mini-Language<\/a><\/p>\n
Slice<\/h4>\n
Understanding slice notation<\/a><\/p>\n
Loop, Iteration<\/h4>\n
Loop better: A deeper look at iteration in Python<\/a>
\nPython Basics: Iteration, Iterables, Iterators, and Looping<\/a><\/p>\n
Exercise<\/h4>\n
W3Resources: NumPy Exercises, Practice, Solution<\/a>
\nMachine Learning Plus: 101 NumPy Exercises for Data Analysis (Python)<\/a>
\nHackerRank: Numpy Challenges<\/a><\/p>\n
<\/p>\n
Week 2<\/h3>\n
How can I draw lines into numpy arrays?<\/a>
\nHow to draw thick anti-aliased lines in SciPy?<\/a>
\nscikit-image – Module: draw<\/a>
\nscikit-image – Shapes<\/a>
\nWikipedia: Line drawing algorithm<\/a>
\nRasterung von Linien<\/a>
\nRasterung<\/a><\/p>\n
<\/p>\n
Week 3<\/h3>\n
Convert NumPy<\/h4>\n
How to convert a boolean array to an int array<\/a><\/p>\n
Histogramm<\/h4>\n
Histograms in Image Processing with skimage-Python<\/a><\/p>\n
<\/p>\n
Week 4<\/h4>\n
Image Processing with Python<\/a><\/p>\n
Python 3 – Built-in Functions<\/a>
\nPython 3 – Built-in Types<\/a><\/p>\n
scikit-image.org<\/h4>\n
Module: transform<\/a><\/p>\n
kite<\/h4>\n
resize<\/a>
\nrescale<\/a><\/p>\n
YouTube<\/h4>\n
Image Analysis in Python with SciPy and Scikit Image | Scipy 2019 Tutorial | Nunez-Iglesias<\/a>
\nImage Analysis in Python with SciPy and scikit-image | SciPy 2018 Tutorial | Stefan van der Walt<\/a>
\n20 – Introduction to image processing using scikit-image in Python<\/a><\/p>\n
ABC<\/h4>\n
Glossary: ABC<\/a>
\nAbstract Base Classes for Containers<\/a><\/p>\n
Iterable \/ Iterator<\/h4>\n
Iter-ables<\/strong> are able to be iterated over. Iter-ators<\/strong> are the agents that perform the iteration.<\/p>\n
Iterators are lazy single-use iterables (not precompiled, just-in-time calculation)<\/p>\n