John Reidar Bartle Mathiassen

Texture Similarity Measure Using Kullback-Leibler Divergence between Gamma Distributions

We propose a texture similarity measure based on the Kullback-Leibler divergence between gamma distributions (KLGamma). We conjecture that the spatially smoothed Gabor filter magnitude responses of some classes of visually homogeneous stochastic textures are gamma distributed. Classification experiments with disjoint test and training images, show that the KLGamma measure performs better than other parametric measures. It approaches, and under some conditions exceeds, the classification performance of the best non-parametric measures based on binned marginal histograms, although it has a computational cost at least an order of magnitude less. Thus, the KLGamma measure is well suited for use in real-time image segmentation algorithms and time-critical texture classification and retrieval from large databases.

Computer Vision‐Based Evaluation of Pre‐ and Postrigor Changes in Size and Shape of Atlantic Cod (Gadus morhua) and Atlantic Salmon (Salmo salar) Fillets during Rigor Mortis and Ice Storage: Effects of Perimortem Handling Stress

The present study describes the possibilities for using computer vision-based methods for the detection and monitoring of transient 2D and 3D changes in the geometry of a given product. The rigor contractions of unstressed and stressed fillets of Atlantic salmon (Salmo salar) and Atlantic cod (Gadus morhua) were used as a model system. Gradual changes in fillet shape and size (area, length, width, and roundness) were recorded for 7 and 3 d, respectively. Also, changes in fillet area and height (cross-section profiles) were tracked using a laser beam and a 3D digital camera. Another goal was to compare rigor developments of the 2 species of farmed fish, and whether perimortem stress affected the appearance of the fillets. Some significant changes in fillet size and shape were found (length, width, area, roundness, height) between unstressed and stressed fish during the course of rigor mortis as well as after ice storage (postrigor). However, the observed irreversible stress-related changes were small and would hardly mean anything for postrigor fish processors or consumers. The cod were less stressed (as defined by muscle biochemistry) than the salmon after the 2 species had been subjected to similar stress bouts. Consequently, the difference between the rigor courses of unstressed and stressed fish was more extreme in the case of salmon. However, the maximal whole fish rigor strength was judged to be about the same for both species. Moreover, the reductions in fillet area and length, as well as the increases in width, were basically of similar magnitude for both species. In fact, the increases in fillet roundness and cross-section height were larger for the cod. We conclude that the computer vision method can be used effectively for automated monitoring of changes in 2D and 3D shape and size of fish fillets during rigor mortis and ice storage. In addition, it can be used for grading of fillets according to uniformity in size and shape, as well as measurement of fillet yield measured in thickness. The methods are accurate, rapid, nondestructive, and contact-free and can therefore be regarded as suitable for industrial purposes.

A Simple Computer Vision Method for Automatic Detection of Melanin Spots in Atlantic Salmon Fillets

In this paper, we describe a simple method for automatic detection of melanin spots in Atlantic salmon fillets. Melanin spots are visible dark spots that reduce the quality grade of the fillets. Atlantic salmon processing lines have several operations that involve manual quality evaluation of fillets. One such operation is the inspection of fillets to detect melanin spots. This inspection is labor intensive, and therefore desirable to automate. Two simple computer vision algorithms for melanin spot detection are presented. One algorithm operates on the red channel of RGB images and the second algorithm uses linear discriminant analysis (IDA) on all three RGB channels. A comparison between these two algorithms shows that, for most detection rates, using LDA gives a lower number of false-detections per fillet. We show that the melanin spot detection task can potentially be automated using computer vision.

High-Speed Weight Estimation of Whole Herring (Clupea harengus) Using 3D Machine Vision

UNLABELLED Weight is an important parameter by which the price of whole herring (Clupea harengus) is determined. Current mechanical weight graders are capable of a high throughput but have a relatively low accuracy. For this reason, there is a need for a more accurate high-speed weight estimation of whole herring. A 3-dimensional (3D) machine vision system was developed for high-speed weight estimation of whole herring. The system uses a 3D laser triangulation system above a conveyor belt moving at a speed of 1000 mm/s. Weight prediction models were developed for several feature sets, and a linear regression model using several 2-dimensional (2D) and 3D features enabled more accurate weight estimation than using 3D volume only. Using the combined 2D and 3D features, the root mean square error of cross-validation was 5.6 g, and the worst-case prediction error, evaluated by cross-validation, was ±14 g, for a sample (n = 179) of fresh whole herring. The proposed system has the potential to enable high-speed and accurate weight estimation of whole herring in the processing plants. PRACTICAL APPLICATION The 3D machine vision system presented in this article enables high-speed and accurate weight estimation of whole herring, thus enabling an increase in profitability for the pelagic primary processors through a more accurate weight grading.

An automated salmonid slaughter line using machine vision

Purpose – The purpose of this paper is to describe a new slaughter line for industrial slaughtering of salmonid fish. Traditionally, slaughtering of farmed salmonids – salmon and rainbow trout – was done manually by bleed cutting with knives. Using the new slaughter line that includes 3D machine vision and a bleed‐cutting robot, slaughtering is almost completely automated – nominally requiring only one person to supervise the line and manually bleed cut the fish not handled by the robot.Design/methodology/approach – The design approach of the salmonid slaughter line focuses on using 3D machine vision and a bleed‐cutting robot with four biaxial pneumatic actuators to handle the slaughtering of pre‐anesthetized salmon and rainbow trout.Findings – Under normal operating conditions, the slaughter line is capable of automatically slaughtering 85‐95 percent of all fish at an average feed rate of 30‐80 salmon/min, and the remaining 5‐15 percent are slaughtered manually. Several issues have been discovered, that ...

A 3D machine vision system for quality grading of Atlantic salmon

A 3D machine vision system for quality grading of Atlantic salmon is proposed.Geometric and color features are extracted from a colored 3D point cloud.Salmon can be accurately graded with respect to deformities and wounds, using support vector machine classifiers. Quality grading of Atlantic salmon (Salmo salar) is currently a task performed manually by human operators. To stay competitive in an increasingly global market, it becomes necessary to take advantage of technology to improve productivity and profitability. The Norwegian salmon industry sees the need to automate quality grading, in order to reduce tedious manual labor and to increase product consistency and production flexibility. A machine vision system for external 3D imaging in color, with a 360? scanning cross-section, has been developed for the purpose of quality grading of Atlantic salmon. The two primary causes of downgraded salmon are deformities and wounds. Two classifiers were developed, based on 3D geometric features and color information, to handle each of these primary causes of downgrading. These classifiers are able to detect deformities and wounds, with discrimination efficiencies of 86% and 89% respectively. This work shows that 3D machine vision can enable real-time automatic quality grading of Atlantic salmon. Many of the methods employed are general enough to translate to other species of fish or similar applications with minor modifications.

Computer vision in the fish industry

Abstract: This chapter discusses the application of computer vision in the fish industry. Applications of computer vision are found in automated systems for sorting, grading and processing of fish and fish products. Computer vision is also used for understanding and optimization of practices related to fisheries, fish farming and fish processing. Based on the applications presented in this chapter, we outline the challenges and benefits related to the use of computer vision in the fish industry and point to some future trends.

Towards robotic post-trimming of salmon fillets

Purpose Practically all salmon fillets produced in Norway are trimmed clean of unwanted fat, bone remnants and other defects according to customer requirements. In today’s modern salmon-processing plants, the trimming operation is performed by a combination of automated trimming machines and manual post-trimming. Manual post-trimming is necessary due to the inability of current trimming machines to obtain satisfactory trimming. The purpose of this paper is to describe the work done so far toward a robotic post-trimming of salmon fillets. Design/methodology/approach A prototype concept system was developed to explore the possibility of robotic post-trimming. The concept is based on 3D machine vision, a high-speed robot manipulator and a flexible light-weight cutting knife. Findings The developed prototype demonstrated the feasibility of detecting a pre-defined object to be trimmed in 3D, and performing the specified trimming cut along a 3D cutting trajectory. Research limitations/implications The developed prototype system was built and integrated – focusing so far only on a single trimming operation: the tail cut. Originality/value The originality in the paper is the description of a prototype integrated system, focused on robotic post-trimming of salmon fillets. The value is in providing a starting point for further development toward a complete robotic post-trimming of salmon fillets.

A Machine Vision System for Robust Sorting of Herring Fractions

Among the rest raw material in herring (Clupea harengus) fractions, produced during the filleting process of herring, there are high-value products such as roe and milt. As of today, there has been little or no major effort to process these by-products in an acceptable state, except for by manual separation and mostly mixed into low-value products. Even though pure roe and milt fractions can be sold for as much as ten times the value of the mixed fractions, the separation costs using manual techniques render this economically unsustainable. Automating this separation process could potentially give the pelagic fish industry better raw material utilization and a substantial additional income. In this paper, a robust classification approach is described, which enables separation of these by-products based on their distinct reflectance features. The analysis is conducted using data from image recordings of by-products delivered by a herring processing factory. The image data is divided into three respective classes: roe, milt, and waste (other). Classifier model tuning and analysis are done using multiclass support vector machines (SVMs). A grid search and cross-validation are applied to investigate the separation of the classes. Two-class separation was possible between milt/roe and roe/waste. However, separation of milt from waste proved to be the most difficult task, but it was shown that a grid search maximizing the precision—the true positive rate of the predictions—results in a precise SVM model that also has a high recall rate for milt versus waste.

Gradual Reduction in Sodium Content in Cooked Ham, with Corresponding Change in Sensorial Properties Measured by Sensory Evaluation and a Multimodal Machine Vision System

The European diet today generally contains too much sodium (Na+). A partial substitution of NaCl by KCl has shown to be a promising method for reducing sodium content. The aim of this work was to investigate the sensorial changes of cooked ham with reduced sodium content. Traditional sensorial evaluation and objective multimodal machine vision were used. The salt content in the hams was decreased from 3.4% to 1.4%, and 25% of the Na+ was replaced by K+. The salt reduction had highest influence on the sensory attributes salty taste, after taste, tenderness, hardness and color hue. The multimodal machine vision system showed changes in lightness, as a function of reduced salt content. Compared to the reference ham (3.4% salt), a replacement of Na+-ions by K+-ions of 25% gave no significant changes in WHC, moisture, pH, expressed moisture, the sensory profile attributes or the surface lightness and shininess. A further reduction of salt down to 1.7–1.4% salt, led to a decrease in WHC and an increase in expressible moisture.