Find research datasets worth reusing

opencc-by-4.0Jul 2020View details →

Fig. 1 Strict consensus cladogram obtained from 45 in Phylogenetic analysis of the tribe Neanurini questions tribal classification of the subfamily Neanurinae (Collembola: Neanuridae)

Fig. 1 Strict consensus cladogram obtained from 45 most parsimonious trees under equal weights. Values of Jackknife support and symmetric resampling are indicated on and below branches, respectively. Only values above 40 are indicated to facilitate the visualisation of the most internal branches. The main clades are indicated with letters (a–e) on branches

Fig. 14 Erythraeus regalis, larva. a in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 14 Erythraeus regalis, larva. a Gnathosoma and idiosoma, dorsal view. b Dorsal opisthosomal seta. c Gnathosoma and idiosoma, ventral view

Fig. 11 Erythraeus cinereus, larva. a Leg I. b Leg II. c Leg III. d Tarsus I. e Tarsus II in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 11 Erythraeus cinereus, larva. a Leg I. b Leg II. c Leg III. d Tarsus I. e Tarsus II (d, e, only specialized setae shown)

Fig. 9 Erythraeus cinereus, larva. a Chelicera. b in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 9 Erythraeus cinereus, larva. a Chelicera. b Gnathosoma (and scutum), dorsal view. c Gnathosoma, ventral view. d Palp tibia. e Palp tarsus

Fig. 8 Erythraeus cinereus, adult. a Palp, medial view. b Crista metopica and eyes. c Dorsal opisthosomal setae. d in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 8 Erythraeus cinereus, adult. a Palp, medial view. b Crista metopica and eyes. c Dorsal opisthosomal setae. d Serratala on genu I. e Serratala on genu IV. f Diversity of serratalae and setae of non-serratalae type on telofemora, genua, and tibiae of legs I–IV

Fig. 6 Erythraeus phalangoides, larva. a in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 6 Erythraeus phalangoides, larva. a Gnathosoma and idiosoma, dorsal view. b Dorsal opisthosomal setae. c Gnathosoma and idiosoma, ventral view. d Seta ps

Fig. 10 Erythraeus cinereus, larva. a in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 10 Erythraeus cinereus, larva. a Gnathosoma and idiosoma, dorsal view. b Dorsal opisthosomal setae. c Gnathosoma and idiosoma, ventral view. d Seta ps

Fig. 12 Erythraeus regalis, adult. a Palp, medial view. b Crista metopica and eyes. c Dorsal opisthosomal setae. d in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 12 Erythraeus regalis, adult. a Palp, medial view. b Crista metopica and eyes. c Dorsal opisthosomal setae. d Serratala on genu I. e Serratala on genu IV. f Diversity of serratalae and setae of non-serratalae type on telofemora, genua, and tibiae of legs I–IV

Fig. 16 Erythraeus regalis, larva. a Leg I. b Leg II. c Leg III. d Genu-tarsus I. e Genu-tarsus II in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 16 Erythraeus regalis, larva. a Leg I. b Leg II. c Leg III. d Genu-tarsus I. e Genu-tarsus II. Tibia-tarsus III (d–f, only specialized setae shown)

Fig. 7 Erythraeus phalangoides, larva. a Leg I. b Leg II. c Leg III. d Tarsus I. e Tarsus II. f in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 7 Erythraeus phalangoides, larva. a Leg I. b Leg II. c Leg III. d Tarsus I. e Tarsus II. f Tarsus III (d–f, only specialized setae shown)

Fig. 5 Erythraeus phalangoides, larva. a in Towards resolving the double classification in Erythraeus (Actinotrichida: Erythraeidae): matching larvae with adults using 28S sequence data and experimental rearing

Fig. 5 Erythraeus phalangoides, larva. a Gnathosoma (and scutum), dorsal view. b Odontus. c Gnathosoma, ventral view. d Palp tarsus

opencc-by-4.0Jun 2017View details →

Fig. 3 Trees obtained under the implied weighting using three concavity values k in First phylogenetic analysis of the tribe Oligaphorurini (Collembola: Onychiuridae) inferred from morphological data, with implications for generic classification

Fig. 3 Trees obtained under the implied weighting using three concavity values k = 6 (a), 9 (b), and 12 (c)

opencc-by-4.0Jun 2017View details →

Fig. 4 Abdominal sternite IV in First phylogenetic analysis of the tribe Oligaphorurini (Collembola: Onychiuridae) inferred from morphological data, with implications for generic classification

Fig. 4 Abdominal sternite IV showing organization of furcal remnant. a, b Oligaphorura ursi Fjellberg, 1984; c Micraphorura gamae Buşmachiu and Weiner, 2013; d Oligaphorura groenlandica (Tullberg, 1876); e Dimorphaphorura inya Weiner and Kaprus, 2014; f Protaphorura eichhorni (Gisin, 1954)

BRAIN Journal-An Enhancement over Texture Feature Based Multiclass Image Classification under Unknown Noise-Figure 8. Performance in 1st Approach for three data set

BRAIN Journal-An Enhancement over Texture Feature Based Multiclass Image Classification under Unknown Noise-Figure 4. Principal stages of image classification system

In computer vision, images or objects are recognised by machine going through two phases shown in the figure 4. First the system is trained with features extracted from sample images in training stage then they are tested on input images in testing stage. The performance of the classifier depends on features extracted from the image. This research work is carried out in three different experiments, first experiment is performed on data set containing the original images of sixteen categories, noisy images are classified in second experiment, and third experiment detects the type of noise affected the image followed by filtering through appropriate filter, then filtered images are classified. The performance of each of the experiment is measured with two approaches. First approach extracts the statistical texture features of the whole image, and the original image of size 128x128 is divided into sixteen blocks of size 32x32 pixels in second approach. Then six statistical texture features discussed in second section are extracted from each of the block producing 96 features from each of the images are used for training and testing stage.

BRAIN Journal-An Enhancement over Texture Feature Based Multiclass Image Classification under Unknown Noise-Figure 1. Sample Images of sixteen categories

An image is often corrupted by noise in its acquisition or transmission. Noise is any undesired information that degrades the image and appears in images from a variety of sources. Basically, there are three standard noise models [17], which model the types of noise encountered in most images; they are additive noise, multiplicative noise and impulse noise. In this work we have considered the occurrence of additive noise. An image function is given by f (x, y) where (x, y) is spatial coordinate and f is intensity at point(x, y). Let f (x, y) be the original image, g(x, y) be the noisy version and η(x, y) be the noise function, which returns random values coming from an arbitrary distribution.

BRAIN Journal-An Enhancement over Texture Feature Based Multiclass Image Classification under Unknown Noise-Figure 7. Performance in experiment 3 for both approaches

Classification of noisy images starts with detection of type of noise followed by appropriate filtering operation. Then similar approaches are followed for feature extraction as discussed in above experiments.

BRAIN Journal-An Enhancement over Texture Feature Based Multiclass Image Classification under Unknown Noise-Figure 4. Feed Forward Back propagation Neural Network

This BPNN provides a computationally efficient method for changing the weights in feed forward network, with differentiable activation function units, to learn a training set of input-output data. Being a gradient descent method it minimizes the total squared error of the output computed by the net. The aim is to train the network to achieve a balance between the ability to respond correctly to the input patterns that are used for training and the ability to provide good response to the input that are similar. A typical back propagation network of input layer, one hidden layer and output layer is shown in figure 4.

BRAIN Journal-An Enhancement over Texture Feature Based Multiclass Image Classification under Unknown Noise-Figure 6. Performance in experiment 2 for both approaches

Second experiment is performed on noisy data set with 50 images each class for training of feed forward neural network, and 100 images each class are used for testing phase. This experiment is also carried out with two approaches as discussed in first experiment.

BRAIN Journal-An Enhancement over Texture Feature Based Multiclass Image Classification under Unknown Noise-Figure 9. Performance in 2nd Approach for three data set

This work also deals with classification of multi class images under different constraints of data set. The first experiment is carried out on images without noise, second with Gaussian noise and filtered data set in third experiment. Performance of the classifier using statistical texture features for two approaches are presented in the table 3. It is observed that performance n the first experiment is best in the first data set i.e. data set without noise in both the approach, while the performance is decreased if the same images are affected by Gaussian noise. This is because the texture feature of the original images consists Gaussian pattern also. Filtering of the noise from the second data set improves the result. The table also shows that feature extraction using blocking of the image enhance the average classification rate in all the case.