/CNN

Using Convolutional Neural Networks to solve image processing problems

Primary LanguageJupyter Notebook

CNN

Using Convolutional Neural Networks to solve Computer Vision Problems

Part 1

Domain: Botanical research

Context A University is currently undergoing some research involving understanding the characteristics of plant and plant seedlings at various stages of growth. They already have have invested on curating sample images. They require an automation which can create a classifier capable of determining a plant's species from a photo

Description The dataset comprises of images from 12 plant species. Source: https://www.kaggle.com/c/plant-seedlings-classification/data

Objective University’s management require an automation which can create a classifier capable of determining a plant's species from a photo

Tasks

  1. Importing the data. Analyzing the dimensions of the data. Visualizing the data.

  2. Training, tuning and testing AIML image classifier model using:

    • Supervised learning algorithms for training

    • Neural networks for training

    • CNN for training

  3. Comparing the results from the above steps.

  4. Pickling the best performing model.

  5. Importing a test image to predict the class. Displaying the image. Using the best trained image classifier model to predict the class

Part 2

Domain: Automobile

Context A brand research company wants to understand which cars or car manufacturers are popular in a certain area of the city or locality. Company has a team which takes pictures of the cars randomly through the day. Using this the company wants to set up an automation which can classify the make of the car once the picture has been given as an input.

Tasks

  1. Building the image dataset to be used by the AI team to build an image classifier data.
  2. Importing and displaying the images in python against their labels.

Part 3

Domain: Botanical research

Context A University is undergoing research involving understanding the characteristics of flowers. They already have have invested on curating sample images. They require an automation which can create a classifier capable of determining a flower’s species from a photo

Data Description The dataset comprises of images from 17 plant species. Can be downloaded from TensorFlow [ tflearn.datasets.oxflower17 as oxflower17 ]

Objective University requires an automation which can create a classifier capable of determining a flower’s species from a photo

Tasks

  1. Importing the data. Analyzing the dimensions of the data.

  2. Preprocessing the data.

  3. Data visualisation:

    • Displaying the images

    • Displaying the labels

    • Displaying images vs labels

    • Apply different filters [ for example: blur, contour, edge detection, emboss, smooth etc.] on the images and displaying the image.

  4. Training, tuning and testing AIML image classifier model using:

    • Using supervised learning algorithms for training

    • Using neural networks for training

    • Using CNN for training

    • Using various CNN with transferred learning models for training

    • Comparing the results from the above step.

  5. Creating a GUI to import the image “Prediction.jpg” and using the above designed AIML image classification model to predict the class/label of this image.