"Group Invariant Scattering." Communications in Pure and Applied Mathematics. Berlin, Heidelberg: Springer Berlin Heidelberg, 2004. “On the Significance of Real-World Conditions for Material Classification.” In Computer Vision - ECCV 2004, edited by Tomás Pajdla and Jiří Matas, 3024:253–66. "Invariant Scattering Convolution Networks." IEEE Transactions on Pattern Analysis and Machine Intelligence. This result is comparable to state-of-the-art performance on the KTH-TIPS database. Using the scattering transform and a simple principal components classifier, we achieved 99.375% correct classification on a held-out test set. In this example, we used wavelet image scattering to create low-variance representations of textures for classification. Set the location property of the imageDatastore to the folder containing the KTH-TIPS database that you have access to.
Untarring the downloaded kth_tips_grey_200x200.tar file is sufficient to provide a top-level folder KTH_TIPS and the required subfolder structure. Each subfolder is named for the class of textures it contains. This example assumes you have downloaded the KTH-TIPS grayscale dataset and untarred it so that the 10 texture classes are contained in separate subfolders of a common folder. The majority of images are 200-by-200 in size. There are 810 images in total with 10 textures and 81 images per texture. The KTH-TIPS dataset used in this example is the grayscale version. This example uses a publicly available texture database, the KTH-TIPS (Textures under varying Illumination, Pose, and Scale) image database. The result of this deep feature extraction is that images in the same class are moved closer to each other in the scattering transform representation, while images belonging to different classes are moved farther apart. Wavelet scattering works by cascading the image through a series of wavelet transforms, nonlinearities, and averaging. Because translations and small deformations in the image do not affect class membership, scattering transform coefficients provide features from which you can build robust classification models.
Wavelet image scattering constructs low-variance representations of images which are insensitive to translations and small deformations. For classification problems, it is often useful to map the data into some alternative representation which discards irrelevant information while retaining the discriminative properties of each class.
0 kommentar(er)
