On the assessment of water-holding capacity of hot- vs cold-boned pork

The effects of time of boning and storage period on creatine kinase (CK) activity, transmission value, drip losses and water-holding capacity (WHC) measured by various methods was investigated. At 40 min post-mortem 30 pig carcasses with pH values > 6·2 in the loin were selected. The right loin of each carcass was hot boned and vacuum packaged immediately. The left loin was cold boned and packaged after overnight chilling at 2 ± 2°C. After 1, 5 and 12 days of storage at 0 ± 1°C, 10 hot- and cold-boned loins were unpacked and sampled. Time of boning did not affect drip losses. At 1 day post-mortem the CK activity was higher in hot- than in cold-boned pork. Sarcomere lengths were not affected by time of boning. The WHC was investigated by two controlled methods. A filter-paper press method was not sensitive enough to assess differences in WHC of hot- vs cold-boned pork. The results of a gravimetric method depended on the sample location. Results of the gravimetric test decreased with increasing storage periods. The results suggest that under the experimental conditions the chilling rates of hot-boned vs carcass-attached muscles were similar.     

Efficient Implementation of the Fuzzy c-Means Clustering Algorithms

This paper reports the results of a numerical comparison of two versions of the fuzzy c-means (FCM) clustering algorithms. In particular, we propose and exemplify an approximate fuzzy c-means (AFCM) implementation based upon replacing the necessary ``exact' variates in the FCM equation with integer-valued or real-valued estimates. This approximation enables AFCM to exploit a lookup table approach for computing Euclidean distances and for exponentiation. The net effect of the proposed implementation is that CPU time during each iteration is reduced to approximately one sixth of the time required for a literal implementation of the algorithm, while apparently preserving the overall quality of terminal clusters produced. The two implementations are tested numerically on a nine-band digital image, and a pseudocode subroutine is given for the convenience of applications-oriented readers. Our results suggest that AFCM may be used to accelerate FCM processing whenever the feature space is comprised of tuples having a finite number of integer-valued coordinates.     

Impact of physical handicaps on operators of agricultural equipment

Physically handicapped farm operators and agricultural workers face barriers which make the completion of many essential farm-related tasks difficult or even impossible. These barriers are especially burdensome with respect to the operation and maintenance of agricultural equipment. This paper reports on work being done at Purdue University to assist handicapped farmers and agricultural workers who wish to continue working in spite of their disabilities. The nature of physical handicaps and proportion of farmers affected by these handicaps is discussed. Potential health and safety risks that these operators are exposed to when operating agricultural equipment are addressed. In addition, a brief overview of the Purdue project and recent activities is provided.     

Recognition of moving objects using feature signatures

An important application of machine vision systems is the recognition of known three-dimensional objects. A major difficulty arises when two or more objects project the same or similar two-dimensional image, often resulting in misclassification and degradation of system performance. The changes in images which result from the motion of objects provide a source of three-dimensional information which can greatly aid the classification process, but this three-dimensional analysis is computationally complex and subject to many sources of error. This work develops a methodology which utilizes the information derived from the apparent changes in object features over time to facilitate the recognition task, without the need to actually recover the three-dimensional structure of the objects under view. The basic approach is to generate a ``feature signature' by combining the feature measurements of the individual regions in a long sequence of images. The static information in the individual frames is analyzed along with the temporal information from the entire sequence. These techniques are particularly applicable in situations where static image processing methods cannot discriminate between ambiguous objects. Two example implementations are presented to illustrate the application of the techniques of object recognition using motion information.