# Is it possible to classify images by vectorizing them (and achieve a good performance)?

Many applications of image classification involves convolutional neural network, where the image is treated directly as a 2D (or 3D, if multiple images) matrix.

I wonder if images can be classified (and with reasonably good performance) with a MLP or softmax regression or even SVMs by vectorizing them, meaning to stack each row or column of this 2D matrix into a single row or column vector and feeding that into the network directly (no convolution)

The answer is probably negative...but I wonder if anyone know whether this is possible.

• An image is usually represented by a 3D tensor, except for gray scale images. Sep 5 '20 at 7:53

Unsurprisingly, CNNs do the best, but his “Neural Nets” category gives a number of fully-connected models with classification error under $$1\%$$. The SVM and KNN categories also report models with error rates under $$1\%$$.