Flower Recognition Research Articles

The Recognition and Esthetical Awareness of Flowers shown in the Prose of the Late Chosun Dynasty -with the prose of Ok-Lee and the metaphor of flowers by the new style writers as the center-

The Recognition and Esthetical Awareness of Flowers shown in the Prose of the Late Chosun Dynasty -with the prose of Ok-Lee and the metaphor of flowers by the new style writers as the center-

Flower Image Recognition Using Multi-Class SVM

This In this paper, a specific system is developed to recognize images of flower types. The proposed automatic flower boundary extraction method consists of two major procedures: the detection of four edge points and boundary tracing. Flower recognition includes two stages: feature extraction and matching. For the flower boundary extraction portion, we present a new technique for automatically identifying a flower’s boundary in an image. For boundary tracing, an intelligent scissors algorithm is applied. The color gradient magnitude cost term is implemented so that it can act directly on the three components of the color image. Suggested extraction of the characteristics has used division of the image in three levels (level 1, level 2, and level 3), the RGB and YCbCr of each level, the minimum Euclidean distance value of eight colors, and the number of petals. Using multi-class SVM, this dissertation derived 97.07% recognition of thirteen different types of flower images.

Host range evolution in a selected group of osmiine bees (Hymenoptera: Megachilidae): the Boraginaceae-Fabaceae paradox

Bees are extraordinarily diverse with respect to host plant choice and adaptation. Recent findings suggest that bee host range might be largely governed by evolutionary constraints related to pollen digestion or flower recognition and handling. In the present study, we applied phylogenetic inference to investigate whether such constraints underlie host plant choice in bees of the Annosmia-Hoplitis group (Megachilidae) and to what extent these bees have evolved specialized adaptations for pollen collection. We demonstrate that most pollen specialist species exclusively exploit either Boraginaceae or Fabaceae, whereas all pollen generalists harvest pollen from both Boraginaceae and Fabaceae. The counterintuitive affinity towards these two plant families, which are neither closely related nor share similar flower morphologies, demonstrates that pollen host choice is considerably constrained in this group of bees. We hypothesize that this Boraginaceae-Fabaceae paradox might be the result of (1) similar secondary metabolites in the pollen of both families; (2) metabolites that can be detoxified by the same physiological tools; or (3) similar pollen nutrient composition. Contrary to the widely held belief that specialized adaptations for pollen collection are rare among bees, such adaptations are common in the Annosmia-Hoplitis bees, where they have evolved several times independently to exploit flowers of widely different morphologies.

Sunlight Fluctuation Compensation for Tomato Flower Detection Using Web Camera

As basic research to develop a machine vision system to detect tomato flowers, a robust color and brightness compensation approach against the sunlight fluctuation was proposed. This approach used the scanning strategy to obtain an uniform condition for precise color and brightness measurement even under changing sunlight illumination. According to the relations between color differences and camera properties, adaptive camera parameter adjustment was calibrated to generate the best possible color correction. Experimental results showed that this method could not only measure tomato flower colors, but also meet the requirements of automatic flower recognition under varying illumination conditions.

Suitability of Feature Extraction Methods in Recognition and Classification of Grains, Fruits and Flowers

This paper presents the suitability of feature extraction methods for the identification and classification of certain agriculture and horticulture crops. Primarily, agriculture/horticulture crops are recognized based on their shape, size, color, texture and the like. When crops exhibit different shapes and sizes, it is customary to choose the shape and size as the basic features. Certain crops are easily identified simply by color; for example, with crops like jowar, ground nut, pomegranate and mango, color becomes the discriminating feature. We have considered color as one of the features in this study. Some agriculture/horticulture crops have overlapping colors, such as wheat and ground nut or mango and orange. When we consider the bulk samples of such grains or fruits, the surface patterns vary from crop to crop. In such cases, the texture becomes ideal for recognition. Hence, we have obtained morphological features, like shape and size, color and textural features, of the image samples to recognize, classify and grade the agriculture/horticulture crops.

Extraction of flower regions in color images using ant colony optimization

Abstract Extraction of flower regions from complex background is a difficult task and it is an important part of a flower image retrieval and recognition. In this article, we propose an Ant Colony Optimization (ACO) algorithm as a general color clustering method, and test it on flower images as a case study of object boundary extraction. The segmentation methodology on flower images consists of six steps: color space conversion, generation of candidate color cluster centers, ant colony optimization method to select optimum color cluster centers, merging of cluster centers which are close to each other, image segmentation by clustering, and extraction of flower region from the image. To evince that ACO algorithm can be a general segmentation method, some results of natural images in Berkeley segmentation benchmark have been presented. The method as a case study on flower region extraction has also been tested on the images of Oxford-17 Flowers dataset, and the results have confronted with other well established flower region extraction approaches.

Leaf and Flower Recognition System (e-Botanist)

Leaf and Flower Recognition System (e-Botanist)

Recognition and Classification of Food Grains, Fruits and Flowers Using Machine Vision

In this paper, we have presented different methodologies devised for recognition and classification of images of agricultural/horticultural produce. A classifier based on BPNN is developed which uses the color, texture and morphological features to recognize and classify the different agricultural/horticultural produce. Even though these features have given different accuracies in isolation for varieties of food grains, mangoes and jasmine flowers, the combination of features proved to be very effective. The average recognition and classification accuracies using colour features are 87.5%, 78.4% and 75.7% for food grains, mango and jasmine flowers, respectively, and the average accuracies have increased to 90.8%, 80.2% and 85.8% for food grains, mangoes and jasmine flowers ,respectively, using texture features. The average accuracies have increased to 94.1%, 84.0% and 90.1% for food grains, mangoes and jasmine flowers, respectively. The results are encouraging and promise a good machine vision system in the area of recognition and classification of agricultural/horticultural produce.

Visible models for interactive pattern recognition

The exchange of information between human and machine has been a bottleneck in interactive visual classification. The visible model of an object to be recognized is an abstraction of the object superimposed on its picture. It is constructed by the machine but it can be modified by the operator. The model guides the extraction of features from the picture. The classes are rank ordered according to the similarities (in the hidden high-dimensional feature space) between the unknown picture and a set of labeled reference pictures. The operator can either accept one of the top three candidates by clicking on a displayed reference picture, or modify the model. Model adjustment results in the extraction of new features, and a new rank ordering. The model and feature extraction parameters are re-estimated after each classified object, with its model and label, is added to the reference database. Pilot experiments show that interactive recognition of flowers and faces is more accurate than automated classification, faster than unaided human classification, and that both machine and human performance improve with use.

Recognition of flowers by pollinators

The flowers of angiosperm plants present us with a staggering diversity of signal designs, but how did this diversity evolve? Answering this question requires us to understand how pollinators analyze these signals with their visual and olfactory sense organs, and how the sensory systems work together with post-receptor neural wiring to produce a coherent percept of the world around them. Recent research on the dynamics with which bees store, manage and retrieve memories all have fundamental implications for how pollinators choose between flowers, and in turn for floral evolution. New findings regarding how attention, peak-shift phenomena, and speed-accuracy tradeoffs affect pollinator choice between flower species show that analyzing the evolutionary ecology of signal-receiver relationships can substantially benefit from knowledge about the neural mechanisms of visual and olfactory information processing.

Priority of color over scent during flower visitation by adult Vanessa indica butterflies

Most flower visitors innately prefer a particular color and scent, and use them as cues for flower recognition and selection. However, in most cases, since color and scent serve as a combined signal, not only does the preference for an individual cue, but also the preference hierarchy among different cues, influence their flower visitation. In the present study, we attempted to reveal (1) the chromatic and (2) the olfactory cues that stimulate flower visiting, and (3) the preference hierarchy between these cues, using the naive adult butterfly Vanessa indica. When we offered 12 different-colored (six chromatic and six achromatic) paper flower models, V. indica showed a color preference for yellow and blue. When we examined the proboscis extension reflex (PER) of V. indica towards 16 individual compounds identified in the floral scents from two nectar plants belonging to the family Compositae, Taraxacum officinale and Cirsium japonicum, six compounds were found to have relatively high PER-eliciting activities, including benzaldehyde, acetophenone, and (E+Z)-nerolidol. When we combined color and scent cues in two-choice bioassays, where butterflies were offered flower models that were purple (a relatively unattractive color), the models scented with these active compounds were significantly more attractive than the odorless controls. In addition, synthetic blends mimicking the floral scents of T. officinale and C. japonicum (at doses equivalent to that of ten flowers) enhanced the number of visits to the scented models. However, the effect of odorizing was not conspicuous in parallel bioassays when yellow flower models were used, and the butterflies also significantly preferred odorless yellow models to scented purple models. These results demonstrate that V. indica depends primarily on color and secondarily on scent during flower visitation.

Flower color affects tri-trophic-level biocontrol interactions

The adults of many parasitoid species require nectar for optimal fitness, but very little is known of flower recognition. Flight cage experiments showed that the adults of an egg parasitoid ( Trichogramma carverae Oatman and Pinto) benefited from alyssum ( Lobularia maritima L.) bearing white flowers to a greater extent than was the case for light pink, dark pink or purple flowered cultivars, despite all cultivars producing nectar. Survival and realised parasitism on all non-white flowers were no greater than when the parasitoids were caged on alyssum shoots from which flowers had been removed. The possibility that differences between alyssum cultivars were due to factors other than flower color, such as nectar quality, was excluded by dying white alyssum flowers by placing the roots of the plants in 5% food dye (blue or pink) solution. Survival of T. carverae was lower on dyed alyssum flowers than on undyed white flowers. Mixing the same dyes with honey in a third experiment conducted in the dark showed that the low level of feeding on dyed flowers was unlikely to be the result of olfactory or gustatory cues. Flower color appears, therefore, to be a critical factor in the choice of plants used to enhance biocontrol, and is likely also to be a factor in the role parasitoids play in structuring invertebrate communities.

Automatic recognition of wild flowers

AbstractIn this paper we propose an automatic recognition system for wild flowers. Two photos, one of the flower and one of the leaves taken from directly above or at a close angle of a single wild flower, were used as a single set. The objective (flower, leaf) is extracted from each image using a clustering method, then recognition is performed using a piecewise linear discriminant function after finding 10 features in the picture of a flower and 11 features in the picture of a leaf. We performed experiments on 20 sets of 34 species of wild flowers that grow around our university campus in the spring and early summer. The results of the experiment showed a recognition rate of 96.0% when all of the features (21) were used. Next we performed an experiment to select the features particularly useful for recognition. These results showed that six features for the pictures of flowers and two features for the pictures of leaves were the most effective, and with them a recognition rate of 96.8% could be reached. © 2003 Wiley Periodicals, Inc. Syst Comp Jpn, 34(10): 90–101, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10099

Chemical and Chromatic Bases for Preferential Visiting By the Cabbage Butterfly, Pieris rapae , to Rape Flowers

Scent and coloration of corolla were examined as floral attributes responsible for preferential visiting by the cabbage butterfly, Pieris rapae, to rape flower, Brassica rapa. Floral volatile components that release the flower-visiting behavior of the butterfly were identified by chemical analyses, electroantennography (EAG), and two behavioral bioassays: proboscis extension reflex (PER) in response to odor and attraction to artificial flowers. GC and GC-MS analyses of the headspace volatiles from the flowers revealed the presence of six aromatic compounds, benzaldehyde, phenylacetaldehyde, benzyl alcohol, 2-phenylethanol, phenylacetonitrile, and indole in decreasing order of quantity. Of these, phenylacetaldehyde elicited the highest response in the PER assay. While benzyl alcohol, 2-phenylethanol, benzaldehyde, and phenylacetonitrile evoked moderate responses, the PER-eliciting activity of indole was very weak. In two-choice behavioral bioassays, artificial flowers scented with any one of these PER-active compounds attracted significantly more butterflies than control (unscented) flowers, whereas those treated with indole were almost inactive. The EAG activities of the six chemicals were not high and were about the same at a low dose (1 μg), but phenylacetaldehyde elicited a much stronger response from both sexes at higher doses (10 and 100 μg). An overall profile of EAG responses at a dose of 100 μg was analogous to that of PER performance, suggesting that floral volatiles may be involved in close-range location or recognition of flowers rather than long-range attraction. By spectroscopic and UV-photographic examinations of rape flower, the central part of the corolla was found to absorb UV rays in marked contrast to the other parts, which reflected near-UV rays (λmax = 350 nm). This indicates that the flower is endowed with a conspicuous nectar guide that is probably an important visual stimulus for attracting foraging adults of P. rapae. Consequently, the present findings strongly suggest that this elaborate pollination strategy of rape flower, characterized by its good combination of olfactory and visual attractiveness, accounts for preferential visiting by the cabbage butterfly to the flower.

Receptor noise as a determinant of colour thresholds.

Inferences about mechanisms at one particular stage of a visual pathway may be made from psychophysical thresholds only if the noise at the stage in question dominates that in the others. Spectral sensitivities, measured under bright conditions, for di-, tri-, and tetrachromatic eyes from a range of animals can be modelled by assuming that thresholds are set by colour opponency mechanisms whose performance is limited by photoreceptor noise, the achromatic signal being disregarded. Noise in the opponency channels themselves is therefore not statistically independent, and it is not possible to infer anything more about the channels from psychophysical thresholds. As well as giving insight into mechanisms of vision, the model predicts the performance of colour vision in animals where physiological and anatomical data on the eye are available, but there are no direct measurements of perceptual thresholds. The model, therefore, is widely applicable to comparative studies of eye design and visual ecology.

Innate recognition of flowers by bumble bees: orientation of antennae to visual stamen signals

The innate behaviour of flower-naive bumble bees (Bombus terrestris, Bombus lucorum) was observed at artificial flowers that consisted of a corolla and a guide area. A set of key stimuli was found to release a sequence of reactions, including the bee's approach, antennal reaction, and landing. For each reaction a binary choice between visual and olfactory signals was presented at the artificial flowers. Approach from a distance was released by the spectral purity of the corolla colour. The antennal reaction, which is the first antennal contact at an artificial flower, and occurs while the bumble bee is in flight, was oriented toward those areas with colours of the highest spectral purity. The landing reaction was released by visual and olfactory signals from the areas contacted during the antennal reaction. The combined presentation of visual signals from the anthers and olfactory signals from the pollen most effectively promoted landing. The antennal reaction allows precise alignment for landing and the antennal tips contact the visually conspicuous guide areas. This leads to effective perception of visual and olfactory stimuli from the guide area. The pollen and anthers, as well as the floral guides, which act as landing signals, of entomophilous flowers (Linaria vulgaris, Melampyrumpratense) possess olfactory qualities. In contrast, the pollen of one anemophilous plant (Pinus cedrus) exhibits no such qualities.

A new interpretation of flower guide colouration: Absorption of ultraviolet light enhances colour saturation

In melittophilous plants the colour pattern of the flowers, as perceived by bumblebees, is a gradient of centripetally increasing spectral purity. This pattern serves as a signal for innate flower recognition in naive bumblebees permitting orientation to flowers and landing on flowers. Structures which make up the total signal pattern can include the background (e.g., green leaves), corollas, and stamens or floral guides. How various colour parameters, such as dominant wavelength, intensity, and spectral purity influence the colour signal pattern of flowers is analyzed. The process of strong absorption of ultraviolet light is shown to be a mechanism for the enhancement of spectral purity in flower guides. The importance of other mechanisms is also demonstrated. The presence of a gradient of centripetally increasing spectral purity in floral colour patterns as perceived by a bumblebee's eyes is demonstrated by a comparison of the spectral reflectance in different parts of the flower and a representation of colour loci in the colour triangle.

Innate Flower Recognition in Bumblebees (Bombus terrestris, B. lucorum; Apidae): Optical Signals from Stamens as Landing Reaction Releasers

AbstractInnate behavioural reactions in bumblebees were observed in flower dummy experiments. In a previous paper, it was shown that the approach of flower‐naive, untrained bumblebees toward flower dummies is released by colour signals, i.e. a gradient of spectral purity. The bumblebees are directed toward that part of a flower dummy which exhibits the highest spectral purity (Lunau 1990). In the present work it is shown that the bumblebees, while still in flight, make contact with this part using their antennal tips. The antennae reaction is followed by a landing reaction which is released by olfactory and optical signals. The specific optical signals of the guide area which release the landing reaction were investigated. Since in the flower dummies which were used, the guide had the highest spectral purity, most of the antennae reactions were executed at the guide. The antennae reaction allows for a precise orientation and may involve the stimulation of a specialized area of ommatidia. Minute changes in optical guide parameters could thus be detected. The following features of stamens which most effectively released the landing reaction were: a minimum of 2 theca dummies; an oval shape of theca dummies which face each other along the longitudinal axis (both these characteristics are found in genuine stamens); 4 mm distance between theca dummies (this coincides with the distance between the antennal tips of bumblebees); two equally sized theca dummies each with an area of 7 mm2 (this size of theca dummies was preferred over larger or smaller ones; the latter parameter was not changed when the corolla size was varied). Colour parameters are not involved in releasing the landing reaction. Clearly, bumblebees possess an innate releasing mechanism (IRM) that responds to optical signals of anthers which release the landing reaction. The experimental results are in accordance with conclusions drawn from the comparative studies of Osche (1979, 1983a, 1983b) that many flower guides can be interpreted as stamen mimics. Therefore stamens as well as stamen mimics represent a highly standardized signal for the insect pollinators and they are well suited for innate orientation at flowers.

COVERT AND OVERT RECOGNITION IN PROSOPAGNOSIA

Prosopagnosic patients suffer an inability to recognize familiar people by visual inspection of their faces. Despite the absence of overt recognition, though, some prosopagnosic patients continue to process the identities of familiar faces covertly. A longstanding controversy concerns whether the recognition deficit in prosopagnosia is specific for faces, or also affects other types of visual stimuli. We investigated whether the patient P.H., who has severe problems with within-class recognition of many types of visual stimuli, would show covert recognition for all stimuli which he cannot recognize overtly. Such a finding would be consistent with the idea that face recognition and recognition of other visually similar stimuli are performed by the same underlying functional mechanisms. We assessed this possibility with a forced-choice decision between correct and incorrect alternative names for familiar faces, cars and flowers, and with comparisons of P.H.'s ability to learn true versus untrue names to familiar faces, cars and flowers. Results indicated that P.H. does show covert recognition of cars and flowers, as well as faces. In addition, the covert effects observed in the forced-choice name decision and learning tasks used here were shown to have a potential common basis. Finally, the possibility of using covert knowledge as a basis for rehabilitation was explored. As was observed by Sergent and Poncet (1990) in their patient, P.H. could achieve some overt face recognition under very specific circumstances.

A Hypothesis Concerning the Prevalence of Red Coloration in California Hummingbird Flowers

The prevailing view that the prevalence of red colors in the hummingbird flowers of the California and western American flora is related to a preference for red, by hummingbirds is not substantiated by experimental evidence. The present paper advances an alternative hypothesis relating common red coloration to the nomadic and migratory habits of the hummingbirds in this region. It is reasoned that quick recognition of hummingbird flowers by hummingbirds which frequently enter new feeding territories is selectively advantageous for both the plants and their bird pollinators. The display of the same red floral color by the different plant species in the whole area of migration facilitates this quick recognition.