In aquaculture breeding programs where large numbers of fish need to be rapidly phenotyped, the absolute physical dimensions of fish (in millimeters or inches) are often required to be extracted from electronic images in order to measure the size of the fish. While it is possible to infer the length of the fish in pixels, the absolute scale of the image (in pixels-per-millimeter or dots-per-inch) is largely unknown without a reference grid, or requires additional hardware, data collection and/or record-keeping management overheads. One cost and time effective solution is to capture the absolute scale by including a measuring ruler in the photographed scene and from which a computer program can automatically identify the scale of the photo and calculate fish morphometric measurements. To assist such workflow, this study developed an algorithm that automatically detects a ruler in a given image, and automatically extracts its scale as distance (in fractional number of pixels) between the ruler's graduation marks. The algorithm was applied to 445 publicly available images of barramundi or Asian seabass (Lates calcarifer), where a millimeter-graded ruler was included in each image. Convolutional Neural Network (CNN) was trained to segment the images into ruler, background, fish and label sections. Then the distance-extraction algorithm was applied to the ruler section of the images. The false-negative rate was less than 2%, where the ruler graduation distances could not be extracted in only 2-6 (out of 445) images even when the test images were rotated up to 90 degrees. The mean absolute relative error (MARE) of the inferred distances was 1-2%.