Skip to content

GlossaryπŸ”—

Deep learning-relatedπŸ”—


AdamπŸ”—

Adam (adaptive moment estimation) is a first-order gradient-based optimization algorithm for stochastic objective functions, which computes individual adaptive learning rates. In the deep learning methods, this algorithm can be used to minimize the loss function.


AnchorπŸ”—

Anchors are fixed bounding boxes. They serve as reference boxes, with the aid of which the network proposes bounding boxes for the objects to be localized.


AnnotationπŸ”—

An annotation is the ground truth information, what a given instance in the data represents, in a way recognizable for the network. This is, for example, the bounding box and the corresponding label for an instance in object detection.


AnomalyπŸ”—

An anomaly means something deviating from the norm, something unknown.


BackboneπŸ”—

Part of a pretrained classification network. Its task is to generate various feature maps, which is why the classifying layer has been removed.


Batch sizeπŸ”—

The dataset is divided into smaller subsets of data, which are called batches. The batch size determines the number of images taken into a batch and thus processed simultaneously.
Hyperparameter: 'batch_size'


Bounding boxπŸ”—

Bounding boxes are rectangular boxes used to define a part within an image and to specify the localization of an object within an image.


Change strategyπŸ”—

The strategy, when and how hyperparameters are changed during the training of a DL model


Class agnosticπŸ”—

Class agnostic means without the knowledge of the different classes.

In HALCON, we use it for reduction of overlapping predicted bounding boxes. This means, for a class-agnostic bounding box suppression, the suppression of overlapping instances is done ignoring the knowledge of classes, thus strongly overlapping instances get suppressed independently oftheir class.


ClassπŸ”—

Discrete categories (for example, β€œapple”, β€œpeach”, β€œpear”) that the network distinguishes. In HALCON, the class of an instance is given by its corresponding annotation.


ClassifierπŸ”—

In the context of deep learning: The classifier takes an image as input and returns the inferred confidence values, expressing how likely the image belongs to every distinguished class. For example, the three classes β€œapple”, β€œpeach”, and β€œpear” are distinguished. When giving an image of an apple to the classifier, the resulting confidences β€œapple”: 0.92, β€œpeach”: 0.07, and β€œpear”: 0.01 could be returned.


COCOπŸ”—

Abbreviation for β€œcommon objects in context”, a large-scale object detection, segmentation, and captioning dataset. There is a common file format for each of the different annotation types.


ConfidenceπŸ”—

Number expressing the affinity of an instance to a class. In HALCON, the confidence is the probability, given in the range of [0,1].
Alternative name: score


Confusion matrixπŸ”—

Table comparing the classes predicted by the network (top-1) with the ground truth class affiliations. It is often used to visualize the performance of the network on a validation or test set.


Convolutional Neural Networks (CNNs)πŸ”—

Neural networks used in deep learning, characterized by the presence of at least one convolutional layer in the network. They are particularly successful for image classification.


DataπŸ”—

In the context of deep learning, the instances to be recognized (for example, images) and their appropriate information concerning the predictable characteristics (for example, the labels in case of classification)


Data augmentationπŸ”—

Generation of altered copies of samples within a dataset. This is done to augment the richness of the dataset, for example, through flipping or rotating.


DatasetπŸ”—

Dataset refers to the complete set of data used for a training. The dataset is split into three, if possible disjoint, subsets:

The training set contains the data on which the algorithm optimizes the network directly.

The validation set contains the data to evaluate the network performance during training.

The test set is used to test possible inferences (predictions), thus to test the performance on data without any influence on the network optimization.


Deep learningπŸ”—

Originally used to describe the training of neural networks with multiple hidden layers, today it is rather used as a generic term for several different concepts in machine learning. In HALCON, β€œdeep learning” is used for methods using a neural network with multiple hidden layers.


EpochπŸ”—

In the context of deep learning, an epoch is a single training iteration over the entire training data, i.e., over all batches. Iterations over epochs should not be confused with the iterations over single batches (for example, within an epoch).


ErrorsπŸ”—

In the context of deep learning, we refer to error when the inferred class of an instance does not match the real class (for example, the ground truth label in case of classification). Within HALCON, error in particular refers to the top-1 error.


Feature mapπŸ”—

Output of a given layer


Feature pyramidπŸ”—

Group of feature maps, whereby every feature map origins from another level, i.e., it is smaller than its preceding levels.


HeadπŸ”—

Heads are subnetworks. For certain architectures, they attach on selected pyramid levels. These subnetworks proceed information from previous parts of the total network o generate spatially resolved output, for example, for the class predictions. They generate the output of the total network and hence constitute the input of the losses.


HyperparameterπŸ”—

Like every machine learning model, CNNs contain many formulas with many parameters. During training, the model learns from the data in the sense of optimizing the parameters. However, such models can have other, additional parameters, which are not directly learned during the regular training. These parameters have values set before starting the training. We refer to this last type of parameters as hyperparameters to distinguish them from the network parameters that are optimized during training. Hyperparameters are solver-specific parameters. Examples: the initial learning rate or the batch size


Inference phaseπŸ”—

Stage when a trained network is applied to predict (infer) instances (which can be the total input image or just a part of it) and eventually their localization. Unlike during the training phase, the network is not changed anymore in the inference phase.


In-distributionπŸ”—

In-distribution refers to data that comes from the same underlying distribution as the data on which a model was trained. When a model encounters in-distribution data during inference, the data is similar in terms of its statistical properties, features, and patterns to what the model has seen before during training.


Intersection over UnionπŸ”—

The intersection over Union (IoU) is a measure to quantify the overlap of two areas. We can determine the parts common in both areas, the intersection, as well as the united areas, the union. The IoU is the ratio between the two areas intersection and union.
The application of this concept may differ between the methods.


LabelπŸ”—

Arbitrary strings used to define the class of an image. In HALCON, these labels are given by the image name or by the directory name, for example, β€œapple_01.png”, β€œpear.png”, β€œpeach/01.png”.


Layer, hidden layerπŸ”—

Building block in a neural network, thus performing specific tasks (for example, convolution, pooling). It can be seen as a container, which receives weighted input, transforms it, and returns the output to the next layer. Input and output layers are connected to the dataset, i.e., the images or the labels, respectively. All layers in between are called hidden layers.


Learning rateπŸ”—

Weighting with which the gradient is considered when updating the arguments of the loss function. In simple words, when optimizing a function, the gradient defines the direction into which is optimized, and the learning rate determines how far along this direction it is stepped. Hyperparameter: 'learning_rate'
Alternative names: Ξ», step size


LevelπŸ”—

Denotes the whole group of layers within a feature pyramid network, whose feature maps have the same width and height. The input image represents level 0.


LossπŸ”—

Compares the prediction from the network with the given information, what to find in the image (and, if applicable, also where), and penalizes deviations. The loss function is optimized during the training process to adapt the network to a specific task.
Alternative names: objective function, cost function, utility function


MomentumπŸ”—

Used for the optimization of the loss function arguments; μ ∈ [0,1). When the loss function arguments are updated (after having calculated the gradient), a fraction μ of the previous update vector of the past iteration step is added. This has the effect of damping oscillations. When μ is set to 0, the momentum method has no influence.
In simple words, when updating the loss function arguments, we still remember the step we did for the last update. Now we go a step in direction of the gradient with a length according to the learning rate and additionally we repeat the step we did last time, but this time only ΞΌ times as long.
Hyperparameter: 'momentum'


Non-maximum suppressionπŸ”—

In object detection, non-maximum suppression is used to suppress overlapping predicted bounding boxes. When different instances overlap more than a given threshold value, only the one with the highest confidence value is kept while the other instances, not having the maximum confidence value, aresuppressed.


Out-of-DistributionπŸ”—

Refers to data that significantly differs from the data on which a model was trained. When a model encounters out-of-distribution data during inference, the data’s statistical properties, features, or patterns are unfamiliar to the model, leading to potential challenges in making accurate predictions.


OverfittingπŸ”—

Happens when the network starts to β€œmemorize” training data instead of learning how to find general rules for the classification. This becomes visible when the model continues to minimize error on the training set but the error on the validation set increases. Since most neural networks have a huge amount of weights, these networks are particularly prone to overfitting.


RegularizationπŸ”—

Technique to prevent neural networks from overfitting by constraining their weights. Simply put, regularization favors simpler models that are less likely to fit to noise in the training data and generalize better. L2 regularization works by adding an extra term to the loss function, which penalizes the squared magnitude of the weights. Weight decay, on the other hand, directly shrinks the magnitude of the weights by a small factor in each iteration of the training. Hyperparameters: 'weight_prior', 'weight_decay'
Alternative names: regularization parameter, weight decay parameter, Ξ»

In HALCON, Ξ» is used for the learning rate. Within formulas, Ξ± is used for the regularization parameter.


RetrainingπŸ”—

Defined as updating the weights of an already pretrained network, i.e., during retraining the network learns the specific task.
Alternative name: fine-tuning.


SGDπŸ”—

See Stochastic gradient descent.


SolverπŸ”—

Optimizes the network by updating the weights in a way to optimize (i.e., minimize) the loss.


Stochastic gradient descentπŸ”—

Iterative optimization algorithm for differentiable functions. A key feature of the SGD is to calculate the gradient only based on a single batch containing stochastically sampled data and not all data. With deep learning methods, this algorithm can be used to calculate the gradient to optimize (i.e., minimize) the loss function.


Top-k errorπŸ”—

For a given image class, the classifier infers confidences of how likely the image belongs to every distinguished class. Thus, for an image we can sort the predicted classes according to the confidence value the classifier assigned. The top-k error tells the ratio of predictions where the ground truth class is not within the k predicted classes with highest probability.
In case of a top-1 error, we check if the target label matches the prediction with the highest probability. In case of a top-3 error, we check if the target label matches one of the top 3 predictions (the three labels getting the highest probability for this image).
Alternative name: top-k score


Transfer learningπŸ”—

Refers to the technique where a network is built upon the knowledge of an already existing network. In concrete terms this means taking an already (pre-) trained network with its weights and adapt the output layer to the respective application to get your network. In HALCON, we also see the following retraining step as a part of transfer learning.


UnderfittingπŸ”—

Occurs when the model over-generalizes. In other words, it is not able to describe the complexity of the task. This is directly reflected in the error on the training set, which does not decrease significantly.


WeightsπŸ”—

In general, weights are the free parameters of the network, which are altered during the training due to the optimization of the loss. A layer with weights multiplies or adds them with its input values. In contrast to hyperparameters, weights are optimized and thus changed during the training.

Filtering-relatedπŸ”—


SmoothingπŸ”—

Applying a filter function on the given data to capture the main data patterns while removing noise


Random noiseπŸ”—

Stationary variation of brightness or color information by a small random amount for every pixel with an assumed mean of 0 over the total image


Systematic noiseπŸ”—

Predictable noise, for example caused by the specific setup used to acquire the images

Identification-relatedπŸ”—


Data code symbolπŸ”—

Two-dimensional graphical symbol that encodes characters and numbers. It is constructed by dark and light dots, bars, or small squares called modules. There are different types of data codes. Two common types are stacked codes and matrix codes.


Stacked codeπŸ”—

Type of data code symbol that contains a stack of 1D bar codes arranged in rows and columns. To ensure that the complete stack of 1D bar codes is processed, the symbol contains a start and a stop pattern. Additionally, the symbol is framed by a quiet zone.


Matrix codeπŸ”—

Type of data code symbol that uses graphical patterns consisting of dark and light modules arranged in two dimensions. The symbol consists of three components: a finder pattern, a data pattern, and a quiet zone.


ModuleπŸ”—

Dark and light dots, bars, or small squares that are used to build a bar or data code symbol


Quiet zoneπŸ”—

Homogeneous frame around the symbol’s border, which makes the symbol better distinguishable from the background or from other objects in the image


Finder patternπŸ”—

Pattern that is used to find the symbol and its orientation in the image. The pattern differs depending on the used bar or data code type.


Image Source-relatedπŸ”—


DeviceπŸ”—

The actual imaging device. This includes different kinds of sensors, ranging from conventional machine vision cameras to 3D sensors and, in special cases, controllers or virtual devices.


GenICamπŸ”—

The GenICam standard allows machine vision devices to expose their configuration properties to the connected application via a feature description XML file. HALCON image sources rely on this standard to provide access to the device configuration (see set_image_source_param and get_image_source_param). Usually, HALCON users do not need to deal with these XML files directly. The standard defines a wide range of features, many of which go beyond the scope of this documentation. For more detailed information, consult the official standard documents, particularly the GenICam Standard Features Naming Convention (SFNC) and the GenICam GenTL SFNC. These resources are hosted by the European Machine Vision Association (EMVA).


GenTLπŸ”—

The GenICam GenTL standard allows machine vision applications and frameworks from different vendors to access machine vision cameras and devices from different other vendors. It specifies a clearly defined software interface that allows to hide different implementation details from the using application. An application like HALCON using different GenTL producers like the plugins can also be referred to as GenTL consumer.


Image source handleπŸ”—

Provides a generic interface to a wide variety of underlying image acquisition standards and technologies. From the viewpoint of the HALCON library, any image source handle provides the same basic operations. The image source handle ties together software and hardware components that are needed to acquire images.


InterfaceπŸ”—

The hardware interfacing with the imaging device, for example, where the cable coming from the imaging device is plugged into the host machine. Thus, in the image source context, the term β€œinterface” does not refer to what was formerly called the image acquisition interface. If framegrabbers are used, each framegrabber card is typically modeled as one interface. Per default, HALCON image sources hide the complexity of multiple interface by automatically using the correct one.


ModuleπŸ”—

The individual units of an image source (plugin, interface, device, stream). Each module allows access to its parameters. The module names therefore also apply to parameter groups of the same name.


PluginπŸ”—

Abstract the various technologies used to transfer images from the imaging device to the receiving application, also referred to as GenTL Producer. Plugins exist in form of .cti files on each target machine. Plugins can be selected and installed with the MVTec Software Manager (SOM). Plugins (i.e., GenTL Producers) provided by other manufacturers are automatically available after installing the manufacturer’s proprietary SDK. Consult the manufacturers documentation for more in depth instructions. At runtime, plugins not provided by MVTec are found by HALCON through the environment variable GENICAM_GENTL64_PATH (or GENICAM_GENTL32_PATH), which lists all the paths that contain .cti files.


StreamπŸ”—

A device can allow access to none, one, or multiple streams of images. The typical machine vision camera just gives access to one stream. Per default, HALCON image sources hide the complexity of multiple streams.

Measurement-relatedπŸ”—


Annular arcπŸ”—

A circular arc with an associated width


Measure objectπŸ”—

Data structure containing a specific region of interest that is prepared for the extraction of straight edges, which lie perpendicular to the major axis of a rectangle or an annular arc


Metrology modelπŸ”—

Data structure containing all metrology objects, all information needed for the measurement, and the measurement results


Metrology objectπŸ”—

Data structure for the object to be measured with 2D metrology. The metrology object is represented by a specific geometric shape for which the shape parameters are approximately known. Additionally, it contains parameters that control the measurement, for example, parameters that specify the dimension and distribution of the measure regions.


Measure regionsπŸ”—

Rectangular regions that are arranged perpendicular to the boundaries of the approximate objects. Within these regions, the edges that are used to get the exact shape parameters of the metrology objects are extracted.


RANSACπŸ”—

RANSAC (RANdom SAmple Consensus) is an iterative method to estimate parameters of a mathematical model from a set of observed data that contains outliers. It is a non-deterministic algorithm producing a reasonable result only with a certain probability, which increases as more iterations are allowed. The algorithm is used in the measurement process to fit the edge positions inside all measure regions to geometric shapes.

Morphology-relatedπŸ”—


Input regionπŸ”—

Region that is modified by morphological operators


Non-linear operatorπŸ”—

Operator that does not necessarily preserve structures of the input image


Structuring elementπŸ”—

Region that is used to scan the input image


Texture inspection-relatedπŸ”—


Training imagesπŸ”—

Images that are used for training


Test imagesπŸ”—

Images that are compared to the trained texture inspection model


PatchπŸ”—

Collection of neighboring pixels


Texture featureπŸ”—

The pixel values within a patch


SampleπŸ”—

A texture feature that is used for training


Novelty scoreπŸ”—

In the test process, the texture features of the test images are compared to the texture inspection model and their novelty score is calculated. The larger this value, the more probable it is that the individual texture feature does not fit to the texture inspection model.


Novelty thresholdπŸ”—

Threshold determined during the training process. Texture features with a novelty score below the novelty threshold fit to the texture inspection model. Texture features with a higher novelty score do not.