Creates 4-dimensional blob from image or series of images

blob = cv.Net.blobFromImages(img)
blob = cv.Net.blobFromImages(imgs)
blob = cv.Net.blobFromImages(..., 'OptionName',optionValue, ...)

Input

• img input image (with 1-, 3- or 4-channels).
• imgs input images (all with 1-, 3- or 4-channels).

Output

• blob 4-dimansional array with NCHW dimensions order.

Options

• Size spatial size for output image [w,h]. default [0,0] (in which case input image size is used)
• Mean scalar with mean values which are subtracted from channels. Values are intended to be in (mean-R, mean-G, mean-B) order if image has BGR ordering and SwapRB is true. default [0,0,0]
• ScaleFactor multiplier for images values. default 1.0
• SwapRB flag which indicates that swap first and last channels in 3-channel image is necessary. For instance, Caffe models are usually trained on BGR images, while TensorFlow models expect RGB images as input. default true
• Crop flag which indicates whether image will be cropped after resize or not. default true

Creates blob and optionally resizes and crops the images from center, subtracts mean values, scales values, and swaps blue and red channels.

If Crop is true, input image is resized so one side after resize is equal to corresponding dimension in Size and another one is equal or larger. Then, crop from the center is performed. If Crop is false, direct resize without cropping and preserving aspect ratio is performed.

A blob is a 4-dimensional matrix (so-called batch) with the following shape: [num, cn, rows, cols].