Tag: common general knowledge

Image classification / STMICROELECTRONICS – T 1148/05 – 27 May 2009

In this decision, a method of image classification was claimed. The Board assumed that all features contribute to the technical character and that the sufficiency of disclosure was given.

Object of the Invention:

  • image classification method for classifying digital images into photographs, texts, and graphics
  • conventional heuristic methods implemented by expert systems present a number of drawbacks, in particular the computational complexity required for analysing the large number of pixels of an image
  • another problem is touched on by the “impossibility of optimising analysis using parallel architectures”
  • the thrust of the application is for constructing a classification algorithm (“tree-structured classifier”) which is both powerful in terms of class discrimination and efficient in terms of processing speed

Board I (sufficiency of disclosure (Article 83 EPC):

  • examining division has argued that the application does not disclose any specific example of a tree classifier adapted to a specific set of image classes
  • however, the application does disclose the “high-level classification problem” (i.e. to distinguish photographs from graphics and texts, see paragraphs 0002 and 0046) and it discloses that 72 lowlevel features have been chosen (from among 389 features, for example, see paragraphs 0016 and 0052) to carry out the test described in paragraphs 0047 to 0053
  • background of that choice may lack detail but it still provides the general teaching that a (sub-)set of low-level features can be chosen according to general criteria (discrimination power and efficiency, column 3, lines 22 to 25) and managed in any combination (paragraph 0020) to build a classifier fulfilling a set of conditions (see e.g. paragraphs 0021/0022, 0039, 0042)

Board II (inventive step):

  • all features are assumed to contribute to the technical character of the claimed subject matter
  • general aspects of processing and pre-classifying digital images are old
  • however, the claimed method derives novelty from the use of a large library of 22 specific technical image parameters (low-level features) which are not disclosed in combination in any of the available prior art documents
  • Article 56 EPC 1973 asks for an inventive technical contribution (T 641/00-Two identities/COMVIK)
  • the following line of argument guides the skilled person in an obvious manner from the prior art to the claimed method:
    • classification of digital images for the adoption of the most suitable image-processing strategies has become “an indispensable need“, see application
    • according to D2, which may be used as a starting point, Web images are classified into photographs and graphics
    • in digital image processing, it is well-known (and inevitable) to construct a classification algorithm before it is used for classifying images
    • when constructing an algorithm for classifying digital images, it is well-known to accomplish this by way of a tree classifier using features or parameters which describe a digital image, see e.g. the prior art referred to in the application itself
    • invention mainly differs from prior art by the library of specific low-level features for improving the classification result
    • however, it is evident that all the image features which are known to describe properties of digital images are natural candidates for distinguishing images and classes of images, from each other
    • the skilled person has an expectation of improvement in that any low-level feature is prima facie suitable for discriminating image classes at least at a high level.
    • the skilled person designing a binary classification tree obviously prefers features having a great power of discriminating two classes (see e.g. D3, page 4, second paragraph)
    • the application itself presents most of its low-level features as forming part of the prior art
    • regarding the few features for which no prior art has been cited in the application, the application still conveys the impression that those features represent usual parameters for describing and analysing digital images
    • otherwise, if they were fundamentally new to the image processing person, they would have to be disclosed in much greater detail
    • –> no inventive step

Measurement for a diaper – T 2803/18 – 13 December 2022

This decision concerns an invention comprising a mathematical method. The invention includes the input of sensor signals. However, the Board decided that this was not relevant to the question of whether the non-technical features contribute to the technical character, because there is no technical interaction of the mathematical method on the output side, or no technical implementation of the mathematical method. Nevertheless, the Board considered the non-technical features in the inventive step assessment and found them obvious.

Object of the Invention

  • method for processing sensor signals representing a wetness event in an absorbent article
  • Claim 1 differs from the closest prior art in that it is comprising certain mathematical method steps (comparing vectors with representative vectors of clusters, determining the most similar, allocating the vector to a cluster, based on a mathematical model) to indicate volume of exudate in the absorbent article in a wetness event

Respondent (patent owner):

  • the mathematical method steps contribute to a technical effect
  • relying on point 99 of the Reasons in G 1/19, claim 1 was directed to an indirect measurement or at least to an accurate estimation of the exudate volume collected in an absorbent article

Board (part I):

  • claim only relates to the processing and analysis of sensor signals received from a sensor and results in a more or less accurate estimation of the volume of collected exudate
  • the results obtained by the claimed method are not necessarily more accurate, since the accuracy would depend on many factors (size of training sets, number and type of elements/variables constituting the representative vectors, etc.), none of which are defined in claim 1
  • whether the processing method in the present case may be qualified as an indirect measurement envisaged may be left undecided here, for reasons mentioned below
  • it may just be added that the determination of the volume of a single or of multiple successive wetness events does not provide any technical effect in the sense that the so determined volume necessarily affects the control of any component of the system composed, for example, of an absorbent article comprising sensors and an appropriate processor
  • further, the method does not necessarily imply any action on some other system or a modification of the operation of the system executing the claimed method going beyond the normal physical interaction between the program and the computer
  • -> absent of any technical effect

Board (part II) (assumption of a technical effect):

  • considering in favour of the respondent, that the estimation of the volume of exudate could be seen as a technical effect, to which the distinguishing feature step (mathematical method) further contributs
  • objective technical problem could only be seen in providing an alternative method of processing sensor signals representing wetness events in an absorbent article
  • irrespective of whether the processing method could be considered to involve a technical effect, the subject-matter of claim 1 lacks an inventive step in view of the obvious combination of the method known from the closest prior art with common general knowledge
  • –> no inventive step

Conclusion

The below figure shows according to G 1/19, point 85 and 86 how and when “technical effects” or “technical interactions” based on inter alia non-technical features may occur in the context of a computer-implemented process.

In this decision T 2803/18, input data of a sensor is claimed. However, the claimed mathematical method/non-technical features do not lead to a technical effect on the output side or to a technical effect based on a technical implementation. Therefore, according to the Board, the claimed method could not be considered to involve an inventive step. However, presumably because of the sensor/ sensor signals on the input side, the Board assumed a technical effect and then examined the inventive step based on the non-technical features.