From 9765eccfd006cee92e4cb16aa81331623a2abe2a Mon Sep 17 00:00:00 2001 From: Chaohao Liu Date: Tue, 28 Jul 2026 20:13:06 +1000 Subject: [PATCH 1/2] add traditional features; --- src/traditional/features/README.md | 43 +++++++++++++++++++++++++----- 1 file changed, 36 insertions(+), 7 deletions(-) diff --git a/src/traditional/features/README.md b/src/traditional/features/README.md index 72f9a19..bb1ab76 100644 --- a/src/traditional/features/README.md +++ b/src/traditional/features/README.md @@ -1,6 +1,7 @@ # Traditional Feature Extraction This folder contains the traditional feature extraction work for the project. +There is shared link of the ## Current Files @@ -250,18 +251,46 @@ The raw image files are not committed to Git. Both methods were tested on images from different classes and produced fixed-length feature vectors. -## Current Branch +## Downloading Traditional Feature Files -Current branch: +The extracted traditional feature files are stored separately on OneDrive because the `outputs` folder is not tracked by Git. -`Chaohao_TraditionalFeature3` +Download the feature files from: -This branch continues the pipeline by combining the HOG and colour features. +[Traditional feature files on OneDrive](https://unsw-my.sharepoint.com/:f:/g/personal/z5528581_ad_unsw_edu_au/IgAsAxZV1fJQSbL1AAmSgGoaAU-ZRhVTJmVLsHFxH7leipA) + +After downloading, place the files in: + +```text +outputs/traditional_features/ +``` + +The expected files are: + +```text +train_combined_features.npz +validation_combined_features.npz +test_combined_features.npz +``` + +Each `.npz` file contains: + +```text +features +labels +file_paths +``` + +These files are generated by `features.ipynb` and can be loaded by `cache.ipynb` or `traditional_classifier.ipynb`. + +The expected folder structure is: ```text -HOG: 6084 -Colour: 96 -Combined: 6180 +outputs/ +└── traditional_features/ + ├── train_combined_features.npz + ├── validation_combined_features.npz + └── test_combined_features.npz ``` ## Maintenance From a495484e01feb22fad1cf355487fd4857ddbaea7 Mon Sep 17 00:00:00 2001 From: Chaohao Liu Date: Tue, 28 Jul 2026 20:48:03 +1000 Subject: [PATCH 2/2] improve text --- src/traditional/features/README.md | 11 ++- src/traditional/features/cache.ipynb | 83 ++----------------- src/traditional/features/color.ipynb | 12 +-- src/traditional/features/combine.ipynb | 42 +++++----- .../{fearures.ipynb => features.ipynb} | 4 +- src/traditional/features/sift.ipynb | 36 ++++---- 6 files changed, 47 insertions(+), 141 deletions(-) rename src/traditional/features/{fearures.ipynb => features.ipynb} (99%) diff --git a/src/traditional/features/README.md b/src/traditional/features/README.md index bb1ab76..9b913b9 100644 --- a/src/traditional/features/README.md +++ b/src/traditional/features/README.md @@ -1,7 +1,6 @@ # Traditional Feature Extraction This folder contains the traditional feature extraction work for the project. -There is shared link of the ## Current Files @@ -242,14 +241,14 @@ The raw image files are not committed to Git. ## Validation -| Feature | Shape | Data type | -| --- | --- | --- | +| Feature | Shape | Data type | Output length | +| --- | --- | --- | --- | | HOG | `(6084,)` | `float32` | Fixed | | RGB colour histogram | `(96,)` | `float32` | Fixed | | Combined HOG and colour | `(6180,)` | `float32` | Fixed | | SIFT descriptors | `(N, 128)` | `float32` | Variable | -Both methods were tested on images from different classes and produced fixed-length feature vectors. +The HOG, colour, and combined features produced fixed-length vectors. SIFT produced a variable number of 128-dimensional descriptors. ## Downloading Traditional Feature Files @@ -299,6 +298,6 @@ When adding a new feature: - use the shared settings from `config.py` - accept a PIL image as input -- return a one-dimensional `float32` NumPy array -- keep the output length fixed +- return `float32` NumPy arrays +- clearly state whether the output is fixed-length or variable-length - test the method on images from different classes diff --git a/src/traditional/features/cache.ipynb b/src/traditional/features/cache.ipynb index 3390530..130c262 100644 --- a/src/traditional/features/cache.ipynb +++ b/src/traditional/features/cache.ipynb @@ -7,7 +7,7 @@ "source": [ "# Traditional Feature Cache\n", "\n", - "This notebook loads the combined HOG and RGB colour feature files created by `features.ipynb`.\n", + "This part loads the combined HOG and RGB colour feature files created by `features.ipynb`.\n", "\n", "It does not extract the features again. It loads the saved train, validation, and test features and prepares them for `traditional_classifier.ipynb`.\n", "\n", @@ -47,9 +47,9 @@ "source": [ "## 2. Find the project root\n", "\n", - "The notebook is stored inside `src/traditional/features/`.\n", + "It is stored inside `src/traditional/features/`.\n", "\n", - "This cell searches upward until it finds the main project folder containing `src`, `outputs`, and `.gitignore`." + "Searches upward until it finds the main project folder containing `src`, `outputs`, and `.gitignore`." ] }, { @@ -263,7 +263,7 @@ "source": [ "## 7. Define the cache loading function\n", "\n", - "This function loads one dataset split from its `.npz` file.\n", + "Load one dataset split from its `.npz` file.\n", "\n", "It returns:\n", "\n", @@ -707,79 +707,6 @@ ")" ] }, - { - "cell_type": "markdown", - "id": "5ac13b73", - "metadata": {}, - "source": [ - "## 15. Visualise the HOG and colour feature boundary\n", - "\n", - "Display the end of the HOG section and the complete RGB colour histogram section from one cached feature vector." - ] - }, - { - "cell_type": "code", - "execution_count": 21, - "id": "7581ab65", - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "sample_index = 0\n", - "\n", - "boundary_start = 5984\n", - "boundary_end = 6180\n", - "\n", - "boundary_feature = X_train[\n", - " sample_index,\n", - " boundary_start:boundary_end\n", - "]\n", - "\n", - "feature_indices = range(\n", - " boundary_start,\n", - " boundary_end\n", - ")\n", - "\n", - "plt.figure(figsize=(12, 4))\n", - "\n", - "plt.plot(\n", - " feature_indices,\n", - " boundary_feature\n", - ")\n", - "\n", - "plt.axvline(\n", - " x=6084,\n", - " linestyle=\"--\",\n", - " label=\"Colour feature starts\"\n", - ")\n", - "\n", - "plt.title(\n", - " \"Boundary Between HOG and Colour Features\"\n", - ")\n", - "\n", - "plt.xlabel(\n", - " \"Feature Index\"\n", - ")\n", - "\n", - "plt.ylabel(\n", - " \"Feature Value\"\n", - ")\n", - "\n", - "plt.legend()\n", - "plt.tight_layout()\n", - "plt.show()" - ] - }, { "cell_type": "markdown", "id": "53cbd484", @@ -787,7 +714,7 @@ "source": [ "## Summary\n", "\n", - "This notebook loads the combined HOG and RGB colour feature files created by `features.ipynb`.\n", + "Load the combined HOG and RGB colour feature files created by `features.ipynb`.\n", "\n", "The files are loaded from:\n", "\n", diff --git a/src/traditional/features/color.ipynb b/src/traditional/features/color.ipynb index 14398dd..92dbc29 100644 --- a/src/traditional/features/color.ipynb +++ b/src/traditional/features/color.ipynb @@ -1,15 +1,5 @@ { "cells": [ - { - "cell_type": "markdown", - "id": "2698ae8b", - "metadata": {}, - "source": [ - "Extract an RGB colour histogram from each image.\n", - "\n", - "The red, green, and blue channel histograms are normalised and combined into one fixed-length feature vector." - ] - }, { "cell_type": "markdown", "id": "7b1019cf", @@ -17,7 +7,7 @@ "source": [ "# Colour Histogram Feature Extraction\n", "\n", - "It extracts colour histogram features from the iNaturalist images." + "Extract colour histogram features from the iNaturalist images." ] }, { diff --git a/src/traditional/features/combine.ipynb b/src/traditional/features/combine.ipynb index 1dfc7b4..3f51a8b 100644 --- a/src/traditional/features/combine.ipynb +++ b/src/traditional/features/combine.ipynb @@ -17,7 +17,7 @@ "id": "d79d4428", "metadata": {}, "source": [ - "## 1.Import libraries" + "## 1. Import libraries" ] }, { @@ -44,9 +44,9 @@ "id": "fb4d7786", "metadata": {}, "source": [ - "## 2.Load the shared project configuration\n", + "## 2. Load the shared project configuration\n", "\n", - "It finds the project root and imports `config.py`.\n", + "Find the project root and imports `config.py`.\n", "\n", "Using the shared configuration avoids personal absolute paths and keeps the notebook working on different computers." ] @@ -94,9 +94,9 @@ "id": "ed08813c", "metadata": {}, "source": [ - "## 3.Load and check a sample image\n", + "## 3. Load and check a sample image\n", "\n", - "It selects a sample image from the training set, checks that the file exists, loads it as an RGB image, and displays its basic information.\n", + "Select a sample image from the training set, checks that the file exists, loads it as an RGB image, and displays its basic information.\n", "\n", "Change `sample_index` to test another image." ] @@ -188,11 +188,11 @@ "id": "5ccbc08f", "metadata": {}, "source": [ - "## 4.Define the HOG feature function\n", + "## 4. Define the HOG feature function\n", "\n", - "This function uses the same HOG settings as `hog.ipynb`.\n", + "Use the same HOG settings as `hog.ipynb`.\n", "\n", - "It resizes the image, converts it to grayscale, and returns a fixed-length `float32` feature vector." + "Resize the image, converts it to grayscale, and returns a fixed-length `float32` feature vector." ] }, { @@ -224,11 +224,11 @@ "id": "103c08d1", "metadata": {}, "source": [ - "## 5.Define the colour histogram function\n", + "## 5. Define the colour histogram function\n", "\n", - "This function uses the same RGB histogram method as `color.ipynb`.\n", + "Use the same RGB histogram method as `color.ipynb`.\n", "\n", - "It resizes the image, calculates a 32-bin histogram for each RGB channel, normalises each histogram, and combines them into one `float32` feature vector." + "Resize the image, calculates a 32-bin histogram for each RGB channel, normalises each histogram, and combines them into one `float32` feature vector." ] }, { @@ -268,9 +268,9 @@ "id": "7ab0b3dd", "metadata": {}, "source": [ - "## 6.Define the combined feature function\n", + "## 6. Define the combined feature function\n", "\n", - "This function extracts the HOG feature and RGB colour histogram from the same image.\n", + "Extract the HOG feature and RGB colour histogram from the same image.\n", "\n", "The two feature vectors are then joined into one fixed-length `float32` vector." ] @@ -298,11 +298,9 @@ "id": "a52de3be", "metadata": {}, "source": [ - "## 7.Test the combined feature\n", + "## 7. Test the combined feature\n", "\n", - "It extracts the HOG, colour, and combined features from the sample image.\n", - "\n", - "It checks the output shape, data type, and whether the combined feature contains invalid values." + "Extract the three feature vectors from one sample image and check the final output." ] }, { @@ -342,11 +340,9 @@ "id": "980f7173", "metadata": {}, "source": [ - "## 8.Check the combined feature sections\n", - "\n", - "It checks that the combined feature keeps the correct order.\n", + "## 8. Check the feature order\n", "\n", - "The first part should match the HOG feature, and the remaining part should match the colour feature." + "Check that the HOG values come first and the colour values come after them." ] }, { @@ -391,7 +387,7 @@ "id": "951a4f93", "metadata": {}, "source": [ - "## 9.Test images from different classes\n", + "## 9. Test images from different classes\n", "\n", "It selects sample images from different labels and checks whether the combined feature has the same shape and data type for every image." ] @@ -458,7 +454,7 @@ "id": "96d2157d", "metadata": {}, "source": [ - "## 10.Final validation\n", + "## 10. Final validation\n", "\n", "It performs a final check of the combined feature before it is used in the feature caching pipeline." ] diff --git a/src/traditional/features/fearures.ipynb b/src/traditional/features/features.ipynb similarity index 99% rename from src/traditional/features/fearures.ipynb rename to src/traditional/features/features.ipynb index d432812..32ed126 100644 --- a/src/traditional/features/fearures.ipynb +++ b/src/traditional/features/features.ipynb @@ -1558,9 +1558,9 @@ "id": "92d4e928", "metadata": {}, "source": [ - "## 21. Final validation\n", + "## 21. Final check\n", "\n", - "Perform the final checks on all extracted feature matrices and saved output files." + "Check the final feature files before using them for classifier training." ] }, { diff --git a/src/traditional/features/sift.ipynb b/src/traditional/features/sift.ipynb index e57b11e..6569db7 100644 --- a/src/traditional/features/sift.ipynb +++ b/src/traditional/features/sift.ipynb @@ -94,7 +94,7 @@ "source": [ "## 3. Load and check a sample image\n", "\n", - "It selects one image from the training set, checks the image path, and displays its basic information." + "Select one image from the training set, check the image path, and display its basic information." ] }, { @@ -186,7 +186,7 @@ "source": [ "## 4. Define the SIFT feature function\n", "\n", - "It resizes the image, converts it to grayscale, and extracts SIFT keypoints and descriptors.\n", + "Resizes the image, converts it to grayscale, and extracts SIFT keypoints and descriptors.\n", "\n", "`max_features=500` requests approximately 500 of the strongest keypoints.\n", "\n", @@ -251,7 +251,7 @@ "source": [ "## 5. Test the SIFT feature\n", "\n", - "This cell extracts SIFT keypoints and descriptors from the sample image and checks the output." + "Extract SIFT keypoints and descriptors from the sample image and check the output." ] }, { @@ -292,7 +292,7 @@ "source": [ "## 6. Visualise the SIFT keypoints\n", "\n", - "It draws the detected SIFT keypoints on the resized sample image." + "Draw the detected SIFT keypoints on the resized sample image." ] }, { @@ -342,7 +342,7 @@ "source": [ "## 7. Check the descriptor values\n", "\n", - "It checks the value range and basic statistics of the SIFT descriptors." + "Check the value range and basic statistics of the SIFT descriptors." ] }, { @@ -381,7 +381,7 @@ "source": [ "## 8. Visualise one SIFT descriptor\n", "\n", - "It displays the 128 values of the first SIFT descriptor.\n", + "Display the 128 values of the first SIFT descriptor.\n", "\n", "Each descriptor describes the local gradient information around one detected keypoint." ] @@ -423,7 +423,7 @@ "source": [ "## 9. Test images from different classes\n", "\n", - "This cell tests the SIFT feature extractor on images from different labels.\n", + "Test the SIFT feature extractor on images from different labels.\n", "\n", "The number of descriptors may change between images, but every descriptor must contain 128 values." ] @@ -513,7 +513,7 @@ "source": [ "## 10. Display the test results\n", "\n", - "This cell places the SIFT test results into a table for easier comparison." + "It places the SIFT test results into a table for easier comparison." ] }, { @@ -628,7 +628,7 @@ "id": "e587cb77", "metadata": {}, "source": [ - "## 11.Visualise keypoints from different classes\n", + "## 11. Visualise keypoints from different classes\n", "\n", "Display the detected SIFT keypoints for the selected images from different classes." ] @@ -746,7 +746,7 @@ "source": [ "## 12. Check the descriptor dimensions\n", "\n", - "It confirms that all tested SIFT descriptors contain 128 values." + "Confirm that all tested SIFT descriptors contain 128 values." ] }, { @@ -793,7 +793,7 @@ "\n", "SIFT detects a different number of keypoints in different images.\n", "\n", - "It compares the descriptor row counts produced by the tested images." + "Compare the descriptor row counts produced by the tested images." ] }, { @@ -832,7 +832,7 @@ "source": [ "## 14. Final validation\n", "\n", - "It performs the final checks for the sample SIFT output.\n", + "Perform the final checks for the sample SIFT output.\n", "\n", "The number of descriptor rows may vary between images, but every descriptor must contain 128 values." ] @@ -891,17 +891,11 @@ "source": [ "## Summary\n", "\n", - "SIFT keypoints and descriptors were successfully extracted from the sample images.\n", + "SIFT was used to detect local keypoints and extract 128-dimensional descriptors.\n", "\n", - "- Each SIFT descriptor contains 128 values.\n", - "- The descriptor data type is `float32`.\n", - "- The number of keypoints can be different for each image.\n", - "- `max_features=500` requests approximately 500 of the strongest keypoints.\n", - "- The returned number may be slightly above 500 because one location can produce keypoints with multiple orientations.\n", - "- The keypoint count matches the number of descriptor rows.\n", - "- No missing or infinite values were found.\n", + "Different images produced different numbers of descriptors, so the raw SIFT output does not have a fixed length. Because of this, it cannot be directly added to the current HOG and colour feature vector.\n", "\n", - "Unlike HOG and the RGB colour histogram, SIFT does not directly produce one fixed-length feature vector for each image. A method such as Bag of Visual Words can later convert the SIFT descriptors into a fixed-length representation for classifier training." + "A method such as Bag of Visual Words would be needed before using SIFT with the traditional classifiers." ] } ],