Manjit K. Misra

Thin-Layer Drying and Rewetting Equations for Shelled Yellow Corn

ABSTRACT THIN-LAYER drying and rewetting data for shelled yellow corn have been compiled from all available sources. A thin-layer drying equation was developed us-ing these data with air temperature, air humidity, air velocity and corn initial moisture content as the indepen-dent variables. A thin-layer rewetting equation was also developed. The equation contains air temperature, air humidity and corn initial moisture content as the in-dependent variables.

Acoustic and video imaging system for quality determination of agricultural products

A flexible system for determining the quality of agricultural products based on characteristics such as, for example, mass, shape, hardness, size, color and surface texture is disclosed herein. The quality determination apparatus includes a feeder assembly for sequentially dropping individual product samples upon an impact transducer arrangement. The impact transducer generates transducer signals indicative of the physical characteristics of each product sample. In addition, an imaging device operates to synthesize a digital image representation of each product sample. The transducer signal and digital image representation corresponding to each product are analyzed so as to determine the appropriate degree of quality to be associated therewith.

Implementing a Computer Vision System for Corn Kernel Damage Evaluation

A computer vision system was developed for evaluation of the total damage factor used in corn grading. Major categories of corn damage in the Midwestern U.S. grain market were blue–eye mold damage and germ damage. Seven hundred twenty kernels were obtained from officially sampled Federal Grain Inspection Service (FGIS) corn samples and classified by inspectors on the Board of Appeals and Review. Inspectors classified these kernels into blue–eye mold, germ–damaged, and sound kernels at an 88% agreement rate. A color vision system and lighting chamber were developed to capture replicate images from each sample kernel. Images were segmented via input of red, green, and blue (RGB) values into a neural network trained to recognize color patterns of blue–eye mold, germ damage, sound germ, shadow in sound germ, hard starch, and soft starch. Morphological features (area and number of occurrences) from each of these color group areas were input to a genetic–based probabilistic neural network for computer vision image classification of kernels into blue–eye mold, germ damage, and sound categories. Correct classification by the network on unseen images was 78, 94, and 93%, respectively. Correct classification for sound and damaged categories on unseen images was 92 and 93%, respectively.

Background segmentation and dimensional measurement of corn germplasm

An automatic thresholding technique was developed to segment the background from the images of corn germplasm (ears of corn). The technique was a modification of Otsu’s algorithm using probability theory. Three different measures were used to evaluate the performance of the modified Otsu’s algorithm for background segmentation and subsequent dimensional measurement of corn germplasm. Modified Otsu’s algorithm was found to perform better than Otsu’s algorithm and was successful in automatic background segmentation of all 80 images of corn germplasm included in the study. This modified algorithm also eliminated the misclassification of exposed cob in the image as background which occurred with Otsu’s algorithm. Subsequent dimensional measurements based on the segmentation by the modified algorithm were also highly accurate.

Evaluations of fractal geometry and invariant moments for shape classification of corn germplasm

Abstract Computer vision-based techniques were developed and evaluated for classifying different shapes of germplasms (ear of corn). An algorithm was developed to discriminate round-shaped germplasms based on two features, i.e. circularity and dimensional ratio. Two different approaches based on fractal geometry and higher order invariant moments were used for classification of non-round shaped germplasms. In the fractal-based approach, two additional fractal geometry-based features (i.e. fractal-shape factor and fractal perimeter) were developed and used with fractal dimension and aspect ratio to represent the shape features of the germplasms. Classifications rules based on modified Euclidean measures and distance weighted K -nearest neighborhood were used for classifying the germplasms into one of three non-round-shape classes (cylindrical, cylindrical-conical and conical). Though the overall correspondence for classifying non-round germplasms was 60% (based on 80 samples), a maximum correspondence of 80% could be obtained for classifying cylindrical germplasms (based on 18 samples). Neither method could provide similar classification correspondence for cylindrical-conical germplasms. On the other hand, these methods, however, showed a correspondence of 82.5% for classifying non-round corn germplasms into cylindrical and non-cylindrical (conical and cylindrical-conical) shapes.

Africa's inevitable walk to genetically modified (GM) crops: opportunities and challenges for commercialization.

High relative poverty levels in Africa are attributed to the continents under performing agriculture. Drought, low-yielding crop varieties, pests and diseases, poor soils, low fertilizer use, limited irrigation and lack of modern technologies are among the problems that plague African agriculture. Genetically modified (GM) crops may possess attributes that can help overcome some of these constraints, but have yet to be fully embraced in the mix of technology solutions for African agriculture. Cognizant of this, South Africa, Burkina Faso and Egypt are steadily growing GM crops on a commercial scale. Countries like Kenya, Nigeria, and Uganda are increasingly field-testing these crops with the view to commercialize them. These countries show strong government support for GM technology. Progress by these first adopter nations provides an insight as to how GM crops are increasingly being viewed as one of the ways in which the continent can invigorate the agriculture sector and achieve food security.

CARBON DIOXIDE EVOLUTION FROM FRESH AND PRESERVED SOYBEANS

Carbon dioxide evolution has proven to be a good indicator of deterioration in studies of stored cereal grains and oilseeds. Since little work has been done with stored soybeans, a study was conducted measuring carbon dioxide from stored soybeans using freshly harvested and preserved soybean samples. The objective of the study was to determine the effects of harvesting method, storage temperature, storage moisture content, and storage time on soybean deterioration. Following storage treatment, samples were held under aeration in a respirometer at 26°C and 21% moisture, and evolved carbon dioxide mass was measured until samples had lost 1.0% of original dry matter. At high harvest moistures, combine-harvested soybeans deteriorated faster, but at low harvest moistures, the deterioration rate of hand-harvested soybeans was greater. After 48 weeks of storage, the soybeans harvested at 22% moisture and preserved at -18°C deteriorated in a respirometer like freshly harvested soybeans, but soybeans harvested at 9% deteriorated in a respirometer significantly faster than those freshly harvested at 13% moisture.

Probabilistic Neural Networks for Segmentation of Features in Corn Kernel Images

A method is presented for clustering of pixel color information to segment features within corn kernel images. Features for blue–eye mold, germ damage, sound germ, shadow in sound germ, hard starch, and soft starch were identified by red, green, and blue (RGB) pixel value inputs to a probabilistic neural network. A data grouping method to obtain an exemplar set for adjustment of the Probabilistic Neural Network (PNN) weights and optimization of a universal smoothing factor is described. Of the 14,427 available exemplars (RGB pixel values sampled from previously collected images), 778 were used for adjustment of the network weights, 737 were used for optimization of the PNN smoothing parameter, and 12,912 were reserved for network validation. Based on a universal PNN smoothing factor of 0.05, the network was able to provide an overall pixel classification accuracy of 86% on calibration data and 75% on unseen data. Much of the misclassification was due to overlap of pixel values among classes. When an additional network layer was added to combine similar classes (blue–eye mold and germ damage, sound germ and shadow in sound germ, and hard and soft starch), network results were significantly enhanced so that accuracy on validation data was 94.7%. Image quality was shown to be important to the success of this algorithm as lighting and camera depth of field effects caused artifacts in the segmented images.

Soybean Seed Quality During Conditioning

ABSTRACT EXPERIMENTS were conducted to determine the change in soybean seed quality at various steps in conditioning. Three cultivars, two seed moistures, two temperatures and five conditioning operations were included in the experiments. Handling soybean seeds by a conventional steel-flighting auger decreased seed quality. The airscreen cleaner and the gravity separator improved quality of soybean seedlots. Seedlots below 10% moisture declined in germination as a result of conditioning. Temperature influenced the amount of splits produced during conditioning. Low moisture seedlots conditioned at -8 to —3°C temperatures declined in germination.

Carbon Dioxide Evolution of Fungicide-treated High-moisture Corn

Two corn hybrids, one resistant (FR35 ¥ FR20) the other susceptible (DF20 ¥ DF12) to storage fungi, were harvested and hand-shelled at 22% moisture, wet basis, and stored at this moisture in aerated l-kg bin units. Four Rovral® fungicide treatments plus an untreated control were tested using carbon dioxide evolution as the index of grain-deterioration rate. Equations of carbon dioxide weight versus time were fitted. The resistant corn hybrid manifested a lower deterioration rate than did the susceptible hybrid. Samples treated with fungicide showed a reduction in grain-deterioration rate compared with untreated samples.