Fruit Segments Research Articles

First Report of Postharvest Stemphylium Rot of Mango (Mangifera indica) Caused byStemphylium vesicariumin Pakistan

First Report of Postharvest Stemphylium Rot of Mango (<i>Mangifera indica</i>) Caused by<i>Stemphylium vesicarium</i>in Pakistan

Automatic image segmentation of oil palm fruits by applying the contour-based approach

Nowadays, computer vision-based automation systems in the field of oil palm plantations are still being developed. The ripeness grading for quality control of oil palm fruit and the fruit picking robots are the implementation examples of those systems. Such a system requires a pre-processing called segmentation. Segmentation is a complex process and will be more challenging if the image of oil palm fruit is captured in the natural background moreover with uneven brightness. In this work, the segmentation method of oil palm fruit is proposed by applying the contour-based approach due to the oil palm fruit that has various shapes and colors. This method implemented the Canny algorithm combining with several operations of morphology and reconstruction to remove the noise. The proposed method is evaluated using a local dataset consisting of 160 images with three kinds of ripeness grading (60 raw, 50 under-ripe, and 50 ripe). Overall, the average of segmentation accuracy achieves of 90.13% with the error rates of false positive and false negative are 2.92% and 5.20%, respectively.

Robust image processing algorithm for computational resource limited smart apple sunburn sensing system

Heat and light stress causes sunburn to the maturing apple fruits and results in crop production and quality losses. Typically, when the fruit surface temperature (FST) rises above critical limits for a prolonged duration, the fruit may suffer several physiological disorders including sunburn. To manage apple sunburn, monitoring FST is critical and our group at Washington State University is developing a noncontact smart sensing system that integrates thermal infrared and visible imaging sensors for real time FST monitoring. Pertinent system needs to perform in-field imagery data analysis onboard a single board computer with processing unit that has limited computational resources. Therefore, key objective of this study was to develop a novel image processing algorithm optimized to use available resources of a single board computer. Algorithm logic flow includes color space transformation, k-means++ classification and morphological operators prior to fruit segmentation and FST estimation. The developed algorithm demonstrated the segmentation accuracy of 57.78% (missing error = 12.09% and segmentation error = 0.13%). This aided successful apple FST estimation that was 10–18 °C warmer than ambient air temperature. Moreover, algorithm reduced the imagery data processing time cost of the smart sensing system from 87 s to 44 s using image compression approach.

Recognition of green apples in an orchard environment by combining the GrabCut model and Ncut algorithm

Early detection of green fruits from colour images is important for precise growth status monitoring and production estimation, allowing effective improvement of fruit quality and optimisation of orchard management. Due to the similar colours of the fruit skin and background, variable illumination and occlusions, algorithmic recognition of green apple targets in natural scenes is difficult. To effectively address this problem, a GrabCut model based on the visual attention mechanism was designed for preliminary fruit region extraction of the salient fruits, with a strong anti-noise advantage. For the overlapping fruit targets, the Ncut algorithm was applied to accurately segment the extracted fruits. After fruit segmentation, the three-point circle fitting method was developed to reconstruct each segmented apple target. A total of 200 green apple images were tested in this study. The improved GrabCut algorithm was compared against the standard GrabCut, GBVS (graph-based visual saliency), AIM (attention based on information maximisation), SDSR (saliency detection by self-resemblance), MR (manifold ranking), mean-shift and K-means clustering algorithms. The F1 score of the improved GrabCut model for fruit region extraction was 94.08%, which was 1.92%, 40.62%, 46.98%, 33.58%, 13.89%, 12.89% and 33.74% higher than the scores of the other seven algorithms, respectively. Among them, the improved GrabCut model achieved 100.00% recognition of the 200 apple images. Moreover, a F1 score of 94.12% was achieved by the proposed segmentation and recognition method, and the detection error was 7.37%. Experimental results showed that the proposed method could accurately recognise green apples under natural light conditions.

Fruit sizing in-field using a mobile app

A mobile device based application was developed for manual in-field fruit sizing of mango (Mangifera indica) using machine vision. Fruit on tree were imaged against a hand-held A4 blue background with a scale included, with segmentation of fruit and scale using the b* value of CIE L*a*b* colour space. To correct for depth of field difference between the background and the fruit, the distance between camera and background was estimated using a pin-hole camera model, and the half thickness of the fruit was estimated from allometrics with fruit length and width. RMSE of 3.7 mm on length and 3.6 mm on width was achieved. Fruit allometrics were also used to convert lineal estimates to fruit weight, with a RMSE of 65.9 g achieved.

Nutritional quality of osmotically dehydrated aonla (Emblica officinalisG.) fruit segments

Aonla (Emblica officinalis G.) is an important arid zone fruit crop. It is probably the only fruit to fill the gap of astringent food recommended by the Ayurvedic system of medicine for a balanced diet and sound health. Fruit is a very rich source of ascorbic acid. The highly acidic nature of fruits and limited availability makes it unsuitable for fresh consumption. Various products like murabba, candy, pickle, jam, sauce, squash, syrup are prepared from this fruit. But available information on preparation of dehydrated sweetened aonla segments is limited and during osmodehydration of aonla segments there is a change in biochemical composition of the fruit. Hence, there was a need to study and standardize a simple, economical and appropriate method for preparation of highly acceptable, good quality dehydrated sweetened aonla segments. With this view, the present investigation was undertaken to study osmotic dehydration of aonla fruits using sugar as an osmotic agent. The study was carried out during the year 2014-15 at the Post Harvest Technology laboratory, Horticultural College and Research Institute, Dr. Y.S.R.H.U., Venkataramannagudem, West Godavari district of Andhra Pradesh. These studies were aimed to know the effect of syrup concentrations at 50, 60 and 70 °Brix with solution temperatures of 50, 60 and 70°C maintained initially and later the segments were kept in the solutions for about 24 h of osmosis. The treatments recorded a range of moisture content (10.27-13.67%), ascorbic acid (283.33-208.30 mg 100 g(-1)), titrable acidity (1.90-0.53%), total soluble solids (36.40-56.13 °Brix), total sugars (41.56-65.04%) and total phenols (1230.00-410.00 mg 100 g(-1)) during the storage period. Irrespective of the treatments, no microorganism was detected up to the 120th day of the storage period. However, steeping of segments in 70 °Brix sugar syrup at 70°C for 24 h recorded superior nutritional and organoleptic quality.

Potentiality of freeze-thaw treatment to produce soft textured aonla (Emblica officinalis) candies.

Aonla, due to its astringency, is converted into various processed products. Candy is the most popular of among them. Commercially available aonla candies in India are hard in texture. However, soft textured candies are preferred more over harder ones. Hence, study was undertaken to produce soft textured candies. Whole fruits and fruit segments were blanched in boiled water, frozen in domestic freezer for 12h and thawed at room temperature (15-20°C). Fresh, blanched, frozen and thawed samples were subjected to textural analysis. Some of the blanched and thawed segments were used to prepare candies and subjected to textural analysis. Results indicated that force-deformation behavior of all samples differed significantly. Fresh, blanched, thawed and frozen segments required 14.39, 0.84, 0.22 and 0.18N force, respectively to compress them till 1mm deformation. Similarly, peak force (5mm deformation) was maximum in fresh segments (172.25N) followed by blanched (8.77N), frozen (1.06N) and thawed (0.85N). Peak force values for control and soft candies were 13.14 and 6.86N, respectively. Based on results, it was found that freeze-thaw treatment significantly reduced the firmness of segments and produced soft textured candies.

Combining SUN-based visual attention model and saliency contour detection algorithm for apple image segmentation

Accurate segmentation of apple fruit under natural illumination conditions provides benefits for growers to plan relevant applications of nutrients and pesticides. It also plays an important role for monitoring the growth status of the fruit. However, the segmentation of apples throughout various growth stages had only achieved a limited success so far due to the color changes of apple fruit as it matures as well as occlusion and the non-uniform background of apple images acquired in an orchard environment. To achieve the segmentation of apples with different colors and with various illumination conditions for the whole growth stage, a segmentation method independent of color was investigated. Features, including saliency and contour of the image, were combined in this algorithm to remove background and extract apples. Saliency using natural statistics (SUN) visual attention model was used for background removal and it was combined with threshold segmentation algorithm to extract salient binary region of apple images. The centroids of the obtained salient binary region were then extracted as initial seed points. Image sharpening, globalized probability of boundary-oriented watershed transform-ultrametric contour map (gPb-OWT-UCM) and Otsu algorithms were applied to detect saliency contours of images. With the built seed points and extracted saliency contours, a region growing algorithm was performed to accurately segment apples by retaining as many fruit pixels and removing as many background pixels as possible. A total of 556 apple images captured in natural conditions were used to evaluate the effectiveness of the proposed method. An average segmentation error (SE), false positive rate (FPR), false negative rate (FNR) and overlap Index (OI) of 8.4, 0.8, 7.5 and 90.5% respectively, were achieved and the performance of the proposed method outperformed other six methods in comparison. The method developed in this study can provide a more effective way to segment apples with green, red, and partially red colors without changing any features and parameters and therefore it is also applicable for monitoring the growth status of apples.

Diversity Estimation and Antimicrobial Activity of Culturable Endophytic Fungi from Litsea cubeba (Lour.) Pers. in China

Endophytes are important components of forest ecosystems, and have potential use in the development of medical drugs and the conservation of wild medicinal plants. This study aimed to examine the diversity and antimicrobial activities of endophytic fungi from a medicinal plant, Litsea cubeba (Lour.) Pers. The results showed that a total of 970 isolates were obtained from root, stem, leaf, and fruit segments of L. cubeba. All the fungal endophytes belonged to the phylum Ascomycota and could be classified into three taxonomic classes, nine orders, twelve families, and seventeen genera. SF15 (Colletotrichum boninense) was the dominant species in L. cubeba. Leaves harbored a greater number of fungal endophytes but lower diversity, while roots harbored the maximum species diversity of endophytic fungi. For the antimicrobial activities, seventeen isolates could inhibit the growth of plant pathogenic fungi, while the extracts of six endophytes showed antimicrobial activity to all the tested pathogenic fungi. Among these endophytes, SF22 (Chaetomium globosum) and SF14 (Penicillium minioluteum) were particularly effective in inhibiting seven plant pathogenic fungi growths and could be further explored for their potential use in biotechnology, medicine, and agriculture.

Enhancement-based background separation techniques for fruit grading and sorting

Image processing plays a remarkable role in the automation of fruit grading and sorting. While grading the fruit, accurate extraction of fruit object from the image (background separation) is the chief concern. For extraction of fruit, appropriate segmentation technique is employed; and to accomplish it accurately, enhancement must be performed prior to segmentation. However, majority of the researchers emphasised over fruit segmentation alone. This communication is intended to show the potential of enhancement techniques when combined with fruit image segmentation. Besides, it presents a comparative analysis of enhancement-based background separation techniques for fruit grading and sorting. For this purpose, four main techniques, namely, contrast limited adaptive histogram equalisation (CLAHE) method, Gaussian filter, median filter and Wiener filter were utilised for enhancement and basic global thresholding, adaptive thresholding, Otsu thresholding and Otsu-HSV thresholding were applied for segmentation. 16 sub-models were developed by combining each enhancement method with every segmentation technique. Afterwards, the image quality of the sub-models was validated using quantitative as well as qualitative analyses. Test results demonstrate that CLAHE/Otsu-HSV model outperformed the others for fruit grading and sorting.

Deep Orange: Mask R-CNN based Orange Detection and Segmentation

The objective of this work is to detect individual fruits and obtain pixel-wise mask for each detected fruit in an image. To this end, we presents a deep learning approach, named Deep Orange, to detection and pixel-wise segmentation of fruits based on the state-of-the-art instance segmentation framework, Mask R-CNN. The presented approach uses multi-modal input data comprising of RGB and HSV images of the scene. The developed framework is evaluated using images obtained from an orange grove in Citra, Florida under natural lighting conditions. The performance of the algorithm is compared using RGB and RGB+HSV images. Our preliminary findings indicate that inclusion of HSV data improves the precision to 0.9753 from 0.8947, when using RGB data alone. The overall F1 score obtained using RGB+HSV is close to 0.89.

Segmentation of Apples in Aerial Images under Sixteen Different Lighting Conditions Using Color and Texture for Optimal Irrigation

Due to the changes in the lighting intensity and conditions throughout the day, machine vision systems used in precision agriculture for irrigation management should be prepared for all possible conditions. For this purpose, a complete segmentation algorithm has been developed for a case study on apple fruit segmentation in outdoor conditions using aerial images. This algorithm has been trained and tested using videos with 16 different light intensities from apple orchards during the day. The proposed segmentation algorithm consists of five main steps: (1) transforming frames in RGB to CIE L*u*v* color space and applying thresholds on image pixels; (2) computing texture features of local standard deviation; (3) using intensity transformation to remove background pixels; (4) color segmentation applying different thresholds in RGB space; and (5) applying morphological operators to refine the results. During the training process of this algorithm, it was observed that frames in different light conditions had more than 58% color sharing. Results showed that the accuracy of the proposed segmentation algorithm is higher than 99.12%, outperforming other methods in the state of the art that were compared. The processed images are aerial photographs like those obtained from a camera installed in unmanned aerial vehicles (UAVs). This accurate result will enable more efficient support in the decision making for irrigation and harvesting strategies.

MORPHOLOGICAL AND CHEMICAL CHARACTERISTICS OF VARIOUS PUMMELO (Citrus maxima (Burm.) Merr.) ACCESSIONS FROM MAGETAN REGENCY

Magetan Regency was the production centre of pummelo that have many accessions with various morphological and chemical characteristics, but only a few of them were identificated. This study was aimed at identifying morphological and chemical characteristics of pummelo fruits in Magetan Regency. The study was conducted in the Biology Laboratory of Djuanda University, Bogor from May to July 2015. Results showed with regard to their morphological characteristic, pomelo plants in this region were found to have spheroid and spheroid-pyriform fruits and the weight of their fruit parts, fruit core width, mesocarp thickness, fruit circle before peeling, fruit circle after peeling, number of fruit segments, number of developed seeds, and edible parts of the fruit were varied. Chemical characteristics were also found to be varied with vitamin C content of 29.80−44.66 mg/100g, total soluble solids (TSS) content of 8.10−9.72°Brix, total titratable acidity (TAA) of 0.31−0.53 g/100 ml, and TSS/ TAA ratio of 17.69−28.58. Key words: production centre of pummelo, spheroid, vitamin C, TSS

Automatic segmentation and classification of olive fruits batches based on discrete wavelet transform and visual perceptual texture features

The quality of olive fruit and its virgin olive oil is a main concern for consumers and fruit industrial companies. The effectiveness and fast detection of olive’s skin defects is the most decisive factor in determining its quality. It is necessary to design and implement image processing tools for segmentation and correct classification of the different fresh incoming olive batches. In this paper, we propose a new automatic image segmentation algorithm, based on discrete wavelets transform. The aim of the segmentation algorithm is to discriminate between olives and the background with the challenge of irregular and dispersive lesion borders, low contrast, artifacts in the olive fruit and variety of colors within the interest region. The second part of our work proposes a scheme for olive fruit classification. The classifier first identifies the olive fruit color and then, based upon discrete wavelets transform and Tamura statistical texture features, the healthy olive fruit is distinguished from the damaged one. The new texture feature vector is, then, compared with the robust Local Binary Pattern feature vector. The simplicity of our segmentation and classification algorithms makes them appropriate for designing a productive and profitable computer vision machine.

Design of Smart System to Detect Ripeness of Tomato and Chili with New Approach in Data Acquisition

Manual laxity of fruit ripeness classification is highly influenced by operator subjectivity, thus there is inconsistency for some periods in the classification process. Information Technology development allows fruit identification based on color characteristic by computer aids. A developed system was designed to work on a mobile device with the ability to detect four levels of ripeness of tomato and chili fruits. The acquisition of training data is done with a new approach. Training data came from objective observation of the same fruit of tomato and chili, captured since one month before harvesting until harvesting period. Image segmentation uses K-Means Clustering Method while ripeness detection uses fuzzy logic. The system output consists of types and level of ripeness grouped into four categories: unripe 1, unripe 2, medium, and ripe. This article explains preliminary results of the testing system in static and partial condition using a personal computer before being applied into a mobile-based integrated system. The results showed the level of success for fruit segmentation was 80% for tomato and 100% for chili. The fault is due to the similarity of fruit sample size. The level of success for detecting fruit ripeness is 80% for tomato and 90% for chili. By 10 training data of each, it is shown that the good result with an overall accuracy level of average ripeness detection is 85%.

Recognition and Matching of Clustered Mature Litchi Fruits Using Binocular Charge-Coupled Device (CCD) Color Cameras

Recognition and matching of litchi fruits are critical steps for litchi harvesting robots to successfully grasp litchi. However, due to the randomness of litchi growth, such as clustered growth with uncertain number of fruits and random occlusion by leaves, branches and other fruits, the recognition and matching of the fruit become a challenge. Therefore, this study firstly defined mature litchi fruit as three clustered categories. Then an approach for recognition and matching of clustered mature litchi fruit was developed based on litchi color images acquired by binocular charge-coupled device (CCD) color cameras. The approach mainly included three steps: (1) calibration of binocular color cameras and litchi image acquisition; (2) segmentation of litchi fruits using four kinds of supervised classifiers, and recognition of the pre-defined categories of clustered litchi fruit using a pixel threshold method; and (3) matching the recognized clustered fruit using a geometric center-based matching method. The experimental results showed that the proposed recognition method could be robust against the influences of varying illumination and occlusion conditions, and precisely recognize clustered litchi fruit. In the tested 432 clustered litchi fruits, the highest and lowest average recognition rates were 94.17% and 92.00% under sunny back-lighting and partial occlusion, and sunny front-lighting and non-occlusion conditions, respectively. From 50 pairs of tested images, the highest and lowest matching success rates were 97.37% and 91.96% under sunny back-lighting and non-occlusion, and sunny front-lighting and partial occlusion conditions, respectively.

Starch digestibility and glycemic index of Paranthas supplemented with Citrus maxima (Burm.) Merr. fruit segments.

The present investigation was undertaken to develop paranthas suiting diabetic population with added health benefits. Paranthas were prepared using fresh and dry segments of pomelo. The increase in the concentration of segments decreased the texture value from 1080 to 1022g force (fresh segments) and 1005 to 870g force (dry segments). Naringin along with other bioactive compounds were retained to a greater extent in Paranthas containing dry pomelo fruit segments. Paranthas prepared using 20% (fresh) and 5% (dry) were sensorily acceptable. The pomelo incorporated paranthas had higher levels of resistance starch fractions (12.94%) with low predicted glycemic index (49.89%) compared to control Paranthas at 5.54 and 58.64% respectively. The fortified paranthas with an considerable content of bioactive compounds and low glycemic index indicate the possibility of using it as a dietary supplement. Thus utilization of pomelo fortification helps in improving the nutritional and functional property of paranthas suiting diabetes as well as general population.

Starch digestibility and predicted glycemic index in the bread fortified with pomelo (Citrus maxima) fruit segments

The aim of this study was to evaluate the starch digestibility and predicted glycemic index in breads incorporated with pomelo fruit (Citrus maxima) segments. Volume of the white and brown breads supplemented with pomelo fresh segments increased, while the crumb firmness decreased. Bread with 20% fresh and 5% dry pomelo segments were sensorily acceptable. Bioactive components such as phenolics, flavonoids, naringin and carotenoids were retained to a greater extent in bread containing dry pomelo segments. The pomelo incorporated bread had higher levels of resistant starch fractions (3.87–10.96%) with low predicted glycemic index (62.97–53.13%), despite their higher total starch (69.87–75.47%) content compared to control bread. Thus pomelo segments in the product formulations lowered the glycemic index probably by inhibiting carbohydrate hydrolyzing enzyme activity which could be attributed to naringin. Hence fortified bread prepared from pomelo fruit segment is recommended to gain nutritional value and to decrease the risk of diabetes.

Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards

Ground vehicles equipped with monocular vision systems are a valuable source of high‐resolution image data for precision agriculture applications in orchards. This paper presents an image processing framework for fruit detection and counting using orchard image data. A general‐purpose image segmentation approach is used, including two feature learning algorithms; multiscale multilayered perceptrons (MLP) and convolutional neural networks (CNN). These networks were extended by including contextual information about how the image data was captured (metadata), which correlates with some of the appearance variations and/or class distributions observed in the data. The pixel‐wise fruit segmentation output is processed using the watershed segmentation (WS) and circular Hough transform (CHT) algorithms to detect and count individual fruits. Experiments were conducted in a commercial apple orchard near Melbourne, Australia. The results show an improvement in fruit segmentation performance with the inclusion of metadata on the previously benchmarked MLP network. We extend this work with CNNs, bringing agrovision closer to the state‐of‐the‐art in computer vision, where although metadata had negligible influence, the best pixel‐wise F1‐score of 0.791 was achieved. The WS algorithm produced the best apple detection and counting results, with a detection F1‐score of 0.861. As a final step, image fruit counts were accumulated over multiple rows at the orchard and compared against the post‐harvest fruit counts that were obtained from a grading and counting machine. The count estimates using CNN and WS resulted in the best performance for this data set, with a squared correlation coefficient of .

A robust fruit image segmentation algorithm against varying illumination for vision system of fruit harvesting robot

Vision system is the crucial component of fruit harvesting robot for recognising fruit, however, which is seriously affected by varying illumination when the robot works in real natural environment. A robust fruit segmentation algorithm against varying illumination for vision system was proposed with the aim of effectively extracting fruit object in the natural environment. The method involved the application of improved wavelet transform to fruit image to normalise illumination of object surface. Then Retinex-based image enhancement algorithm was used to highlight fruit object of illumination normalised image. Finally fruit image was segmented by implementing K-means clustering. Three kinds of fruit images of different colour under sunny and cloudy days were segment using the proposed method respectively and the experimental results showed that the proposed algorithm could be robust against the influence of varying illumination and precisely segment different colour fruits.