In OpenCV an "image" is represented by a cv::Mat datatype
Not all Mats are uint8 data type.
Mat initialization can be done in the following way
cv::Mat test = cv::Mat(rows, cols, type)
As an example, to initialize a 640*480 Mat of type uint8 with one channel:
cv::Mat test = cv::Mat(480, 640, CV_8UC1);
In which "CV" is the prefix of all data types, 8 means the number of bytes of each pixel, U stands for unsigned and C1 means that Mat has one channel.
Other examples:
CV_16UC1 : Mat of type unsigned short (uint16) with one channel
CV_32FC3 : Mat of type float with three channels
CV_8UC3: Mat of type unsigned char (uint8) with 3 channels (used to display RGB images)
CV_32SC2: Mat of type signed integer (int32) with two channels
The reason why Uint8 is very common is because it is the standard way to display images, in which each pixel ranges between 0 and 255. If it is a gray scale image, a pixel with value 0 is black and a pixel with value 255 is white, and gray in the middle
Well, Thanks a lot for this amazing answer I have totally understood that uint8 is used since the max value of RGB/BGR channels are 0,255 and uint8 has that range. Got that
But, Why would have an image have another data type that is more than uint8? Since the BGR/RGB channels support only 0,255 values??
Thanks in advance! :)
You got your first reasoning backwards. The RGB/BGR values are [0, 255] BECAUSE uint8 has that range :) It turns out that having 255 possible values for one pixel is enough resolution to have a clear image while not consuming much memory at the same time.
As for the other question, a cv::Mat isn't only needed to display images. A cv::Mat may be used to store any kind of data in the form of a matrix. For example, if you need to perform matrix calculations with floating point precision, uint8 isn't enough. If you have a sensor that outputs data in the range of [0-10000] and need to read it into a cv::Mat, you need uint16 datatype.
Basically OpenCV tries to be as flexible as possible :)
Asked: 2015-10-29 07:14:08 -0600
Seen: 16,869 times
Last updated: Oct 29 '15
