Downloaded 103 times
Uploaded byMuhammad Haroon
Convolutional Neural Network (CNN)
The document discusses the field of computer vision, highlighting its role in enabling computers to process images similarly to humans. It explains the workings of convolutional neural networks (CNNs), detailing their ability to extract features from images and the steps involved in CNNs, including convolution, pooling, flattening, and final classification. Additionally, it notes that CNNs require less pre-processing compared to other classification algorithms.
More Related Content
Similar to Convolutional Neural Network (CNN)
Convolutional Neural Network (CNN)
- 2. Pre-Requisites... Artificial Intelligence hasbeen witnessing a monumental growth in bridging the gap between the capabilities of humans and machines. Researchers work on numerous aspects of the field to make amazing things happen. One of many such areas is the domain of Computer Vision. Computer vision is a field of computer science that works on enabling computers to see, identify and process images in the same way that human vision does, and then provide appropriate output.
- 3.
- 4.
- 5. Convolutional Neural Network(CNN) • A Convolutional Neural Network (CNN) is a Deep Learning algorithm which can take in an input image, assign importance (learnable weights) to various objects in the image and be able to differentiate one from the other. • The pre-processing required in a CNN is much lower as compared to other classification algorithms.
- 6. Learning by ImageFeatures Gray scale image
- 7. How Training isdone? X O Here CNN work as like black box, so what is inside the black box!
- 8.
- 9. 1. Convolutional (SmilingFace) Feature Detector/Filter/Kernel: It extracts some features from our image, stores in separate 2D array and compress the image. HOW? We are going to match Feature detector with original image to compress it.
- 10. 1. Convolutional (of Smiling Face)
- 11. 1. Convolutional (of Smiling Face)
- 12. 1. Convolutional (of Smiling Face) http://setosa.io/ev/image-kernels/ Practical Example of Feature Map!
- 13. A pooling layeris another building block of a CNN. This is basically a function which reduces the pixels of “Feature Map” and change in Pooled Feature Map, Common technique is Max Pooling. 2. Pooling
- 14. Max / Avg.Pooling
- 15. 3. Flattening Flattening isconverting the data into a 1-dimensional array for inputting it to the next layer. We flatten the output of the convolutional layers to create a single long feature vector. And it is connected to the final classification model, which is called a fully- connected layer
- 16.