Python - OpenCV and PyQt5 together

Learn to read and display an image with OpenCV in a PyQt5 workflow, including loading the image path, showing the image in a window, and managing the window wait behavior.

This lecture shows using cv2.waitKey to wait for a key press, map keys to codes with a function, and close the window when a key is pressed.

Read the image, display it, and save it (including changing its extension), then verify saving with a terminal printout and use Q to close.

Learn to capture live video from a webcam using OpenCV in Python, selecting inbuilt or external cameras, checking the camera, reading frames, displaying with imshow, and releasing resources.

This lecture demonstrates saving a live video with a video writer by configuring the output file and format, choosing a codec, setting frame size and fps, and writing frames.

Learn to load an image with OpenCV, draw a line, rectangle, circle, and text, adjust color in bgr order, set thickness, and save or view the edited image.

learn how to convert images to grayscale in OpenCV, using two practical methods, and understand how grayscale reduces noise and the differences between BGR and RGB ordering.

Learn how to compute and plot an image histogram to analyze contrast and intensity distribution, load grayscale images, and visualize the cumulative distribution function to interpret trends.

Leverage histogram equalization to enhance image contrast by adjusting the histogram, view test results on sample images, and learn about resizing images in code.

Explore how thresholding converts grayscale images to binary images to segment objects and identify regions of interest, using simple, adaptive, and mean thresholding methods.

Learn how thresholding in OpenCV separates foreground from background using simple thresholding and adaptive thresholding, including global, binary, and binary inverse methods, with trial-and-error value selection.

this lecture introduces feature detection in images and shows how to identify corners, blobs, and edges using detectors like FAST, SURF, and BRIEF.

Explore canny edge detection in OpenCV by reading an image, applying canny, converting bgr to rgb for display, and comparing the original with the edge-detected result.

Learn contour detection using grayscale conversion, Otsu thresholding, and binary thresholding in OpenCV to extract, count, and draw contours on images.

Learn to detect circles in images using the Hough circles transform in OpenCV, by converting to grayscale, applying blur, and identifying circle centers and radii for visualization.

Count objects in images by converting to grayscale, applying edge detection and thresholding. Find contours, draw them on the image, and count the detected objects with adaptive thresholding.

Discover how to perform blob detection with the SIFT algorithm in OpenCV and PyQt5: load and convert images to grayscale, detect and compute keypoints and descriptors, and visualize them.

Learn how to detect keypoints with SIFT, generate descriptors, and match them between two images using a brute-force nearest-neighbor approach, then visualize the good matches.

Create a main window with PyQt5 and configure the window title. Import widgets, set the window icon and minimum and maximum sizes, then show the window in the application.

Learn how to create and set a fixed menu bar in a PyQt5 window, attach file, view, navigate, and video menus, and display icons for menu items.

Create and customize a toolbar in PyQt5, add and name toolbars, and attach actions like open to respond to user interactions.

Learn how to implement a status bar in a PyQt5 interface, format and display the current date and time, and customize messages and icons for user feedback.

Create a PyQt5 interface with a box layout that splits the main window into a left image area and a right options panel, using image labels and geometry settings.

Learn to style PyQt5 interfaces with a CSS-like stylesheet, name objects, color labels, and build a toolbar and a file menu with submenus and actions such as open and quit.

Connect menu actions to functions in a PyQt5 application using triggered, extend the edit menu, and add copy and paste text functionality.

Learn to load an image from the computer using a file open action, convert it to the correct color format, and display it in a PyQt5 QLabel with proper sizing.

Open an image through a file dialog, capture its path, and display it in a QLabel using PyQt5, with status updates and optional UI feedback.

Learn to build a dropdown menu in PyQt5 by creating a function menu with a drawing shapes submenu, wiring actions like draw line, draw circle, and blur image.

The lecture demonstrates adding more functions to an OpenCV and PyQt5 project, including loading and displaying images, drawing lines, and applying blur.

Explore creating an information message box in PyQt5 for OpenCV apps, including importing the box, creating it, and configuring title and text in the parent window.

Learn to implement a quit confirmation using a PyQt5 message box with a yes/no decision, customizable title and icon, and to show startup messages and download status.

Explore the fundamentals of machine learning, including supervised, unsupervised, and semi-supervised learning, and review classification, regression, and clustering algorithms.

Explore a hands-on k-nearest neighbors demonstration that builds a simple red-and-blue training set, trains a kNN classifier, and classifies a new point using distance and neighbors.

Demonstrates k-means clustering, showing how centroids define two data groups and assign labeled, color-coded clusters with random initialization. Illustrates data preparation, applying means, and visualizing results, including a real-image example.

Learn how to apply k-means clustering to an image by converting pixels to data points, choosing a k value, and reconstructing a color-quantized result for display.

Prepare for recognition by using image segmentation and color analysis, building a four-category dataset, applying circle detection for cropping, and using histograms to distinguish color groups.

Explore segmentation and histogram analysis with OpenCV in Python, including resizing with aspect ratio, grayscale conversion, contrast enhancement via histogram equalization, and histogram computation for images and datasets.

Access the dataset by creating a class to load images from class folders, compute and normalize histograms, and assemble a labeled training set for a classifier.

Build a classifier by selecting a machine learning library, tuning number of neighbors, splitting data into training and testing sets, and training to report accuracy in OpenCV and PyQt5 workflow.

Learn to segment images and detect circles with the Hough transform by converting to grayscale, blurring to reduce noise, then analyze regions of interest with histograms for classification.

Detect circles around images to define regions of interest, extract and mask ROIs, resize to 200x200, compute histograms, and predict classes with a classifier using OpenCV.

Detect circles, create masks, and segment regions to predict classifications, then compare using a nearest-neighbor classifier and histogram validation on the output images.

Create a scaling factor to distinguish coin denominations using OpenCV and PyQt5. Estimate size from the largest detected diameter and apply it to classify 5c, 10c, 20c, and 50c coins.

Apply final steps to a Python app using OpenCV and PyQt5 to detect and count coins, annotate images with text, manage coordinates, and display results with classifier accuracy.

Add a recognition function to the OpenCV and PyQt5 app and connect it to the UI to classify visible items. Show coins detected, the amount, and mean accuracy.

Explore starting and stopping the webcam, capturing live frames, recording video, saving images, and coin detection in a PyQt5 and OpenCV setup, with hands-on demonstrations and guidance.

Thank you for joining this Python, OpenCV, and PyQt5 course; the lecture demonstrates a simple histogram of color approach and a transform for a basic machine learning algorithm.