top of page


The image processing industry has been growing at a steady pace, with rising demand from industries such as healthcare, military, agriculture, and the environment, among others. As an image processing engineer, your options are limitless. Image Processing is one of the emerging technologies. Some of the significant areas of applications include computer vision face detection, forecasting, remote sensing, feature extraction, optical sorting, and medical image processing.

As the name implies, Image Processing is a method that involves conducting various operations on an image to enhance it or collect useful information from it. Image processing can be classified into two categories– analog and digital. Analog image processing is used for hard copies or printouts of images. Image analysts use various visual techniques to interpret the raw data. In digital image processing, computer algorithms help manipulate digital images. Image processing primarily involves three crucial steps – importing the image, analyzing and manipulating the image, and the final output of the modified image based on analysis.

Some main purposes of image processing are —

  • Visualization, where the aim is to identify occluded objects.

  • Image sharpening and restoration to create a finer image.

  • Image retrieval.

  • Image recognition.

  • Measuring various objects in an image.

Image processing :

All the algorithms for preprocessing of full images, segmentation from the background, and color analysis were written in MATLAB 6.5 (The MathWorks, Inc., USA). Preprocessing is the stage preceding the extraction of characteristics, which aims at improving the acquired image and highlighting the features or regions of interest, thus removing distortions and noise while not adding further information to its content. Preprocessing involves techniques to highlight regions and details and to remove any noise which may interfere in the analysis of objects and/or regions of interest. In this context, there is a great variety of techniques from which we can highlight the gray scale and color transformation, as well as thresholding and filtering (Koschan A., 2008).

The segmentation process can be based on the similarity of the color of each pixel and its neighbouring pixels. Sometimes similar pixels, in terms of color, are not part of the same object or feature. The extraction of parameters enables the association between regions of the image and objects in the scene (Gonzalez RC., 2009). After these stages, the image should be ready for the extraction of important characteristics. The final stage— processing—aims to recognize and interpret the images, seeking to make sense of the set of objects of the image, with the goal of improving human visualization and the automatic perception of data in a computer.

Food industry :

n the food industry, image processing systems enable quality assessment, grading, and sorting of different varieties of food items. In the factories, image processing systems can help sort fresh vegetables from rotten ones by inspecting the color, size, shape, and blemishes. The implementation of image processing techniques in this industry is growing at a steady pace especially with the rise of market demand for better products. The food industry is in the top ten industries using computer vision for quality control.[1] With automated visual inspection system becoming increasingly adopted commercially[2], we can watch how image analysis technologies are changing the food production process here and now.


Image processing system inspects food quickly, objectively, reliably and non-destructively, and they have a potential to take on many monotonous tasks traditionally performed by human inspectors. Apart from quality control, they show great results in product grading and counting.

1. Measuring, counting and sorting

Market analysis shows that all other things being equal, customers prefer apples with a maximum diameter between 75 and 80 mm. However, people would have a hard time trying to accurately evaluate a fruit’s size with the naked eye, while a computer vision system can measure a precise diameter of an apple in a blink of an eye, literally.

Automated counting and sorting system based on image analysis can grade fruits, vegetables, nuts, oysters, etc. according to their shape, size and maturity (for fruits and vegetables), increasing the sorting speed by 10 times compared to humans.

2. Quality check

Today, it is possible to inspect the quality of a wide range of food products with a image processing and computer vision system. Both software and hardware parts of the system should be customized to the specific needs of a food company, including inspection goals and the type of product to analyze.

For example, feature extraction and segmentation algorithms will vary significantly depending on the shape, color and texture of an analyzed object, as well as the surrounding scene (the conveyor belt, a crate) and illumination conditions.

3. Packaging

Automated visual check of a filling level and package labeling is another important application of image processing in the food industry. Besides that, a visual system can check the freshness of a packed product with the aid of a special ink changing its color with time and at a different speed depending on the temperature.

Visual inspection is used extensively for the quality assessment of meat products applied to processes from the initial grading through to consumer purchases.

After studying various published paper's I gathered some information about applications of image processing in food industry, which is mentioned below.

Application in Animal Products

Visual inspection is used extensively for the quality assessment of meat products applied to processes from the initial grading through to consumer purchases. (McDonald and Chen.,1990) investigated the possibility of using image-based beef grading in some of the earliest studies in this area. They discriminated between fat and lean in longissimus dorsi muscle based on reflectance characteristics, however poor results were reported. Color, marbling and textural features were extracted from beef images and analysed using statistical regression and neural networks. Their findings indicated that textural features were a good indicator of tenderness. Image analysis was also used for the classification of muscle type, breed and age of bovine meat (Basset, Buquet, Abouelkaram, Delachartre, & Culioli., 2000).

A technique for the spectral image characterisation of poultry carcasses for separating tumourous, bruised and skin torn carcasses from normal carcasses was investigated by Park, Chen, Nguyen, and Hwang (1996). Carcasses were scanned by an intensified multi-spectral camera with various wavelength filters (542–847 nm) with the results indicating that the optical wavelengths of 542 and 700 nm were the most useful for the desired classification.

Storbeck and Daan (2001) measured a number of features of different fish species using an image processing algorithm based on moment invariants coupled with geometrical considerations for discrimination between images of fish as they passed on a conveyor belt at a speed of 0.21 m/s perpendicular to the camera.

Application in Fruits and Vegetables

Potato inspection on the basis of shape, size and color, analysis of defects have been successful achieved using CVS system. In 2010, Barnes et al., developed a new method of detecting defects in potatoes using computational vision. In order to reduce shadow effects and changing conditions of illumination during image acquisition, the potatoes have been placed inside a white cylinder, with daylight lamps placed around the top of it, on a total of 4 lamps. After the segmentation of the potato on the bottom, a pixel classifier was trained to detect spots using extraction of characteristics of the image. Some parameters were used based on statistical information extracted from color and texture of the region surrounding the pixel, and then, an algorithm was used to automatically sort spots and not spots. The result showed that the method was able to classify and optimize the performance of classification with low computational cost, presenting levels of accuracy for white and red potatoes of 89, 6 and 89, 5 %, respectively.

CVS consists of an image acquisition set up, digital image analysis and special sensory color chart to classify objectively potato chips according to their color in different categories. For this purpose, sensory measurements of color in 100 potato chips were correlated with the corresponding objective. Sorting of strawberries based on shape and size was performed using computer vision with accuracy of 98% reported for the developed system. Also CVS system is used to detect the various defects in citrus fruits. Image processing and MATLAB TOOLBOX were used to detect and calculate external appearance of an olive’s skin which is considered to the most decisive factor in determining its quality as a fruit.

Challenges to overcome

Image processing deals with simple identification, measuring and counting better than human vision. However, to achieve this high level of performance, the inspection conditions should be strictly standardized.

For example, object identification becomes much more difficult in a complex scene. Efficient edge detection and segmentation require a homogenous background.

The same applies to light conditions: insufficient and non-uniform illumination obscures shapes of inspected objects and causes false edge detection.

Image processing is evolving rapidly, offering more accurate and reliable techniques for image enhancement, edge detection and segmentation. Advances in machine learning (convolutional neural networks, support vector machines etc.) allow creating the software able to perform classification of features and objects detected in an image more intelligently. With further refinement of image analysis techniques, the food industry can expect that even more visual inspection tasks will be automated in the future.

23 views0 comments

Recent Posts

See All
bottom of page